| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| ... | |
| |
|
|
|
|
| |
A parent whose child tasks are all resolved closes (DONE/CANCELLED + CLOSED) and archives on the next --archive-done; a parent with one or two open children gets those promoted to standalone level-2 tasks first. Carries the leaf-with-notes carve-out (a task whose only descendant is a dated design note is unstarted work, not a finished container — flag NEEDS-USER, never close) and a warning to verify open-child counts against a real subtree scan, not a fragile regex. Depends on --convert-subtasks running first so the counts are accurate.
From the .emacs.d handoff (2026-07-01 task-audit note).
|
| |
|
|
|
|
|
|
| |
Rewrites every level-3+ DONE/CANCELLED/FAILED heading into a dated event-log entry from its CLOSED cookie, enforcing the todo-format depth rule that interactive closes and --archive-done (level-2 only) leave unapplied. A new lint-org checker (subtask-done-not-dated) flags stragglers, and the clean-todo, wrap-up, open-tasks, and task-review workflows now run the converter before archiving.
Removing the CLOSED cookie keeps a DEADLINE or SCHEDULED cookie that shares its planning line, rather than dropping the whole line.
From the .emacs.d handoff (2026-07-01 convert-subtasks bundle).
|
| |
|
|
| |
The new --archive-done aging step's first run on this repo moved 58 closed subtrees older than seven days out of todo.org's Resolved section into archive/task-archive.org, leaving the last week in-file. Confirms the feature end to end: this repo tracks its todo file, so the archive is tracked and no gitignore entry was added.
|
| | |
|
| |
|
|
|
|
| |
org-lint validates links, drawers, blocks, and babel, but not heading well-formedness. These four catch hand-edit defects it stays silent on: an indented heading demoted to body text (the task vanishes from the agenda and never archives), bare stars with no title, a malformed priority cookie org rejected, and a level-2 DONE/CANCELLED with no CLOSED line. All judgment-only and regex-based, wired in after the existing dated-header check. The last one pairs with the new aging step, which archives an undated completed task immediately.
I tightened the indented-heading check to two-or-more stars. The proposed one-or-more-stars regex flagged indented single-star lines, but an indented single * is a valid plain-list bullet, not a lost heading, so it false-positived on legitimate lists (confirmed: three valid bullets flagged). A ** is never a bullet, so an indented one is unambiguously a demoted heading. Added a test that a single-star list stays silent.
|
| |
|
|
|
|
| |
A project's in-file Resolved section grew without bound: --archive-done only moved closures from Open Work into Resolved, same file. .emacs.d's todo.org reached 768KB that way. So --archive-done now has a second step: a Resolved subtree closed longer ago than tc-archive-retain-days (default 7), or with no parseable CLOSED date, moves out to archive/task-archive.org beside the todo file. Only the last week of closures stays in the file. The step honors --check, and tc-archive-retain-days nil disables it.
I added a guard the proposal lacked: the archive inherits the todo file's gitignore status. gitignore-mode projects gitignore todo.org, so without this the aging step would shed previously-private task history into a tracked archive, a leak on any public repo. When the todo file is gitignored and the archive isn't, the script adds the archive path to .gitignore before the first write. Track-mode projects leave both tracked. Covered by two tests in a temp git repo, one per branch.
|
| |
|
|
|
|
| |
The install bin loop linked every script under claude-templates/bin but never pruned orphans, so a deleted script left a dangling ~/.local/bin symlink. page-signal hit exactly this: the wrapper was removed 2026-06-12 but its symlink stayed, resolving to a dead target on the daily drivers. I added a prune step that drops symlinks pointing into claude-templates/bin whose target is gone, so any removed script self-cleans on the next install.
I also added a protocols section naming the two paging channels: notify --persist at the machine, and the signal-mcp send_message_to_user tool when away from it. The pager account was never deregistered (only the page-signal script went away), so the live path is the MCP tool, and the section retires the script for good.
|
| |
|
|
|
|
| |
Recast the speedrun eligibility criteria as checkable gates, not adjectives: dropped the task-size gate so large tasks decompose into per-commit chunks, replaced the act-vs-file rule with a four-item defer checklist keyed on whether the failing test is writable from the task text, and added a pre-flight step that front-loads a run's decisions so it proceeds unattended after. Define :solo: and :quick: precisely enough to enforce in task-review and task-audit.
Also record the spec storage and lifecycle-status decision (org-keyword authoritative, drop the filename suffix) and the requirement to retrofit existing docs across projects.
|
| | |
|
| |
|
|
| |
Task audit. I folded two of Craig's cj decisions: coverage-summary.el stays a local-only helper (reframed from bug to chore, docs work only), and the flashcard-stats refutation exemption goes generic, a header-declared check-exemption that supersedes the old two-option fix. I noted that the unattended-cron task's v1 precondition has landed, so it's buildable now rather than blocked. And I grouped the three flashcard tasks (apkg converter, refutation mode, multi-tag reconcile) under one parent, since they all edit the same two scripts and want building together.
|
| |
|
|
| |
I added route_recommend.py, a pure recommend(item, projects) → (destination, confidence). It has strong, weak, and none tiers, word-boundary literal matching that also handles dot-stripped name aliases, and a deterministic tie-break that downgrades an ambiguous top-tier tie to weak. An empty candidate list yields none. The CLI reuses inbox-send's discover_projects, so the candidate set is the same project universe inbox-send already knows. This covers Phases 1 and 3 of the wrap-up routing spec. The marker and router sub-tasks call it next.
|
| | |
|
| |
|
|
| |
A thin orchestrator that runs the behavior-preserving quality passes over a scope of existing code in order: /refactor, then readability-audit, then it surfaces the :refactor: tasks readability filed and any deferred /refactor findings. It leaves /simplify out, since that works the current diff rather than existing code.
|
| |
|
|
| |
.emacs.d resolves as emacsd and .dotfiles as dotfiles, in both inbox-send and the launch trigger. An exact basename match still wins, and --list shows the stripped name. triggers.md documents the same resolution so the spoken name is consistent across both.
|
| |
|
|
|
|
| |
suspend is a capture-only mid-session pause for an abrupt departure: it writes a resume-weighted entry and leaves the session anchor in place, so the next startup resumes from it. It's the capture half. Startup is the resume half. I registered it with its trigger phrases.
readability-audit is a language-agnostic pass over comments, file headers, names, and organization. The cheap comment and name fixes land inline. Structural findings get filed as :refactor: tasks. It feeds /refactor rather than duplicating it.
|
| |
|
|
|
|
| |
Wrap of the task-audit / blocked-deps / Anki-fix / wrap-teardown-unblock session. Archives the record and applies todo hygiene (Anki and the cancelled Morning-ops subtree archived to Resolved, one table reflowed to 120 cols).
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
| |
:BLOCKS: rulesets: was a malformed org tag, and the property form (:BLOCKED_BY: / :BLOCKS: carrying <project>: <what>) was more structure than the dependency needs. The blocking side now carries a plain :blocker: tag, mirroring :blocked: on the waiting side, with the which-project detail in the task body rather than a property. open-tasks.org reads the body for the blocking/requesting project; the scheme, the todo-format convention, and the inbox blocking-dependency handoff all move to the two-tag form. No property anywhere.
|
| |
|
|
|
|
|
|
| |
The :blocked: tag only marked the waiting side, so a blocker could stay unaware it was holding up another project: the dependency was visible to the one project that couldn't act on it and invisible to the one that could. This closes that gap. Setting :blocked: now requires a reciprocal inbox-send to the blocker, which files the work with a :BLOCKS: <project>: <what> property on its side. open-tasks.org surfaces :BLOCKS: tasks first, since clearing one unblocks another project (the highest-leverage pick), the mirror of pulling :blocked: tasks out of the cascade. Inbox process mode recognizes the blocking-dependency handoff shape, and the convention documents the resolution flow (drop :BLOCKS:, notify the waiter, who lifts :blocked:).
This works for any project pair, since the convention (todo-format.md) and the surfacing (open-tasks.org) live in the shared rule and workflow layer, not in one project.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
|
|
|
|
| |
flashcard-to-anki.py's default_deck_name returned the input basename, so a deck built through flashcard-sync (which passes no --deck) was named after the file slug (refutation-drill) instead of the curated #+TITLE the phone deck should read (Refutations). flashcard-review.org already documented the #+TITLE behavior, and the script never matched it. default_deck_name now scans for a #+TITLE line (case-insensitive, trimmed) and falls back to the basename when there's none.
Five new tests cover title-drives-name, trimming, case-insensitivity, and the two basename fallbacks. The two old tests that asserted basename-always are replaced. The pre-staged script and test (validated 2026-06-21) applied cleanly red-to-green; their redundant copies are removed and the rationale doc kept.
Migration: deck IDs derive from the name, so decks previously built without --deck land as new decks on the next import. Old basename-named decks keep their history and can be deleted by hand.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
Reconciliation keeps each task honest on its own, but a single effort fragmented across several tasks (the agent-agnostic work, say) is hard to see and finish as a whole. Adds Phase C.5: read the open-task set, spot semantic clusters by judgment rather than a brittle keyword match, and propose per cluster either a merge (fold same-work members into one) or a parent-with-children grouping (related-but-distinct members). Proposes, never applies, until Craig picks; broader than Phase C's exact-duplicate fold.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
A task can be blocked by work owed by another project, and today it keeps getting recommended as "next" even though it can't move, while the blocker sits at low priority over there and the dependency stalls silently. Adds a :blocked: tag plus a :BLOCKED_BY: <project>: <what> property (todo-format.md) to mark the dependency, and teaches open-tasks.org Next Mode to pull :blocked: tasks out of the cascade pick and surface them in a dedicated "Blocked on other projects" section that names each blocker and offers an inbox-send nudge. Distinct from VERIFY, which waits on Craig rather than another project.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
|
|
|
|
| |
When a roam edit hits a live org-capture, the guard used to bounce the caller right away (surface to the user, or skip the cycle) even though the capture is usually a few seconds of mid-finalize that clears on its own. capture-guard gets a --wait poll mode: it re-checks every ~10s up to a budget (default 30s, each sleep capped so a short --wait never overshoots), returns the instant the capture clears, and reports blocked only at the deadline. The no-capture common case still returns instantly without sleeping.
Roam mode now uses --wait on every write, and the per-caller fallback fires only after the wait: an interactive run surfaces, the auto /loop defers to the next cycle (the loop cadence is the retry), wrap-up skips and self-heals.
Surfaced live this session: a transient capture blocked a roam reconcile and had cleared a minute later. Covered by three new bats cases (instant-when-safe, timeout-when-blocked, target-after-flag).
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
The wrap-up valediction now always ends with "session wrapped." on its own line — a consistent, unmistakable end-of-session marker, since it's the last user-facing output before Step 6's silent teardown. Craig's request via the roam inbox.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
Audited the 23 open tasks against the git log, recent sessions, and file state. 19 are current. Two were stale: the agent-source task gets a dated note that the agent-neutral wording sweep (6ad0442) and the .emacs.d multi-LLM thread landed, with naming and shared-source extraction still open; the wrap-up-routing marker sub-task is repointed from the deleted process-inbox.org to inbox.org process mode after the 2026-06-23 consolidation. Stamped LAST_AUDIT.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
Wrap of the inbox-consolidation / chime-fix / wrap-teardown / roam-sync session. Archives the session record, stamps the inbox-process marker, and applies todo hygiene (2 completed subtrees archived, one table reflowed to the 120-col standard).
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
|
|
|
|
| |
The roam repo's working tree is dirty most of the time (Craig captures into it constantly, and roam-sync only commits every 15 minutes), so roam mode's pull --ff-only failed on nearly every run and blocked triage. The auto inbox zero loop hit it every cycle.
Roam mode now never pulls. The scan reads the working-tree file directly, since that's already the latest local state, and the rare write removes the claimed items in place and then triggers roam-sync to commit and push. roam-sync already commits-first-then-rebases, so it handles the dirty tree, and the ownership partition (only this project touches its own prefixed lines) means its rebase can't conflict on the edit.
Trade-off: the roam-repo commit carries roam-sync's generic auto-sync message instead of a descriptive one. The provenance for routed tasks lives in the project's todo.org and session log anyway.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
|
|
|
|
|
|
| |
A bare "wrap it up" now tears the session down after the valediction: it kills the ai-term buffer and the aiv-<project> tmux session (which takes claude with it) and restores geometry. "wrap it up with summary" or "and summarize" keeps the buffer. "wrap it up and shutdown" gates on this being the only live ai-term session, then powers the machine off through an abort-able Emacs countdown.
Teardown can't run inline because it kills the session claude runs in, so the valediction would never flush. Step 6 instead drops a basename-keyed sentinel after commit+push is verified, and a new Stop hook (ai-wrap-teardown.sh) does the teardown when the response ends, by which point the valediction has rendered. The hook is a no-op on every normal stop because the sentinel only exists after a teardown wrap.
The runtime lives in .emacs.d/modules/ai-term.el (cj/ai-term-quit, cj/ai-term-live-count, cj/ai-term-shutdown-countdown), and the rulesets side calls it via emacsclient. I routed that companion to .emacs.d, so the feature is end-to-end once it lands. The hook has 8 bats tests. The live teardown and shutdown paths are a manual checklist in todo.org.
Built from the proposal. I went with both summary qualifiers, the Emacs-timer countdown, and the live-count gate.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
|
|
|
|
|
|
| |
I merged process-inbox, monitor-inbox, and inbox-zero into one inbox.org engine. A shared core (value gate, skeptical review, disposition ladder, reply discipline, capture-guard, priority-scheme check) holds the logic that used to be duplicated and cross-referenced across the three files. Each mode (process, monitor, roam) references the core by name instead of restating it.
Every trigger phrase still works, now routing to a mode, so there's nothing to relearn. I added the interactive auto inbox zero mode: ask for an interval, run roam mode on /loop, acknowledge-only on an empty cycle, surface a find to a queue gated on a yes. The fully-unattended /schedule pass stays vNext, tracked separately.
I repointed every live caller (INDEX, protocols, startup Phase C, wrap-up Step 3, triage-intake, broadcast) at inbox.org and its modes, then deleted the three old files. triage-intake and no-approvals stay separate by design. The value gate, dispositions, capture-guard, and reply discipline all behave as before.
Built from the Ready spec. Workflow-integrity and sync-check pass on both the canonical and mirror trees, the stale-reference grep is clean, and the full suite is green.
Claude-Session: https://claude.ai/code/session_017PtX1nt1rtYVATuzmzBS4f
|
| |
|
|
|
|
| |
The inbox-workflow consolidation reached a Ready spec — one inbox.org engine with process/monitor/roam modes, plus "auto inbox zero" as the interactive recurring roam check (the fully-unattended cron pass deferred to vNext).
Files the backlog surfaced while triaging the inbox: the wrap-it-up teardown proposal, the agent-source improvements, the consolidation task itself, and the deferred unattended-cron pass.
|
| |
|
|
|
|
| |
An aborted org-capture can leave a heading with no title and no body (just stars and maybe a TODO keyword). Those belong to nobody and were piling up in the shared roam inbox.
inbox-zero now buckets them as empty in Phase B and removes them in Phase D in the same edit as the claimed items. An empties-only run still enters Phase D and commits, so the sweep runs on every triage, not only when this project owns something. A heading with any title or body is never touched.
|
| |
|
|
|
|
|
|
|
|
| |
Editing the roam inbox on disk while Emacs has an indirect org-capture buffer cloned from it reverts the base buffer under the capture: the capture can't finalize with C-c C-c, and a freshly-typed item can be lost. inbox-zero Phase D edits that file, which Craig captures into constantly, so the collision recurs every session.
I added a capture-guard helper that asks the running daemon whether any CAPTURE buffer's base buffer visits a given file (file-equal-p, so symlinks and path spelling don't matter), exiting non-zero with the names when so. No reachable Emacs or no capture means exit 0, so it never blocks a write that was safe.
Phase D calls it before the pull, not only before the remove, because the ff-only pull also rewrites the file on disk and would wedge a capture the same way. On a collision an on-demand run stops and asks Craig to finalize or abort. The wrap-up sub-step skips the roam reconcile without blocking the wrap, since the items are already filed and the next run reclaims them.
emacs.md gains the inverse of the reload rule: don't yank a file out from under the daemon's live buffers.
|
| |
|
|
| |
Files the remaining inbox proposals as prioritized rulesets tasks, with their design docs preserved under docs/design: the Anki #+TITLE deck-name bug (edited code ready), the apkg to org-drill converter, flashcard-stats refutation mode, an archsetup host-identity guard, the coverage-summary install-location question, and an optional tooling-path enumeration hook.
|
| |
|
|
| |
The no-attribution rules covered AI credit but not incidental mentions of tooling filenames in commit prose. The case that bit: a .gitignore commit naming .claude, CLAUDE.md, and .ai in its message leaks the tooling layer into a public log. Adds a tooling-path-enumeration ban with that gitignore case named, extends the Before-Committing scan, and adds the missing paths to the protocols keep-out list. Both carry the file-is-the-change and private-single-user-repo exemptions, so a rule edit or a rulesets commit can still name what it touched.
|
| |
|
|
|
|
|
|
| |
The spec-review/spec-response pair wrote findings to a sibling <spec>-review.org file that spec-response deleted once processed. The deletion left the iteration-history Artifacts line dangling and dropped the verbatim review. Keeping the file instead collided with spec-response's file discovery and its "no review files remain" done-condition.
Findings now live in the spec under a * Review findings section as TODO tasks with a [/] cookie, the same shape * Decisions already uses. The reviewer records findings there. The responder completes each in place (accept and modify finish DONE, reject finishes CANCELLED with the reason), and the readiness rubric gates on the cookie. A scope-expanding response re-runs the rubric and files any new obligation as a finding or decision before claiming Ready, because resolving every finding can still introduce unreviewed assumptions.
Also folds in two reviewer-practice principles: keep review and response roles explicit, and cite the source for external-dependency facts in a finding. Updates spec-create.org and the workflow INDEX so the trio describes one convention.
|
| |
|
|
| |
The canonical and mirror copies of inbox-zero.org were committed out of sync; the mirror lagged the canonical's two-inbox revision. Bring the mirror up to match.
|
| | |
|
| |
|
|
| |
A `** <YYYY-MM-DD> …` heading carries no keyword, so todo-cleanup's --archive-done can never archive it and task-review drops it from selection. The new level-2-dated-header check (custom, like org-table-standard) emits a judgment item per offending heading so the wrap-up sweep routes it to the next morning's review. Judgment-only, never auto-fixed: the repair needs a DONE-vs-CANCELLED call and the original heading text. Three ERT cases cover it (flagged at level 2, clean for DONE+CLOSED, clean for a level-3 dated entry).
|
| |
|
|
| |
Recent session receipts read "promoted 0 / consulted no" across the board: the wrap-up KB-promotion check existed but fired too late, and nothing surfaced existing lessons to read. This adds the spec's four light prompts plus the read-side step it was missing. Startup gets two Phase C nudges (gated on the roam clone): a consult line listing project-relevant node titles, and a contribute line pointing at the best-practices node. Triage-intake and inbox-zero get a conditional end-of-flow capture reminder that fires only on real signal. Wrap-up gets an early reflection prompt at the top of Step 1 that feeds the existing receipt, so learnings are captured while fresh instead of reconstructed after the Summary. Ratifies the spec's five decisions and adds D6 (the read-side surfacing).
|
| |
|
|
| |
The old rule dated a resolved VERIFY at every depth, including the top level. A level-2 dated header carries no keyword, so todo-cleanup's --archive-done can never archive it and task-review drops it from selection. Now a top-level VERIFY closes like any other top-level task (DONE/CANCELLED + CLOSED:), and dated rewrites are reserved for level 3 and deeper. Updated the rule and the three places that encoded the old behavior: todo-format.md, respond-to-cj-comments.md, and process-inbox.org. Also repaired two pre-existing level-2 dated headers.
|
| |
|
|
| |
Nothing used the cross-agent message system (send/recv/watch/status/discover/halt/resume over the inbox/from-agents/ file-IPC protocol). Every cross-project handoff goes through inbox-send instead. I removed the scripts, READMEs, workflow, tests, INDEX entry, the three startup.org wirings, and the legacy bin symlinks, then repointed helper-mode's escalation to inbox-send and noted the removal in the generic-agent-runtime spec.
|
| |
|
|
| |
I reconciled all 11 open tasks against session history and repo state and refreshed their review stamps. I corrected two stale preambles: helper-instance's shipped detection slices, and memories-sync's claim that work was pending when Phases 0-4 had already shipped. The create-documentation and research-writer skill designs drop to [#D]. Both are designed but unbuilt and wait on a real triggering task, so they shouldn't sit at [#C] against active work.
|
| |
|
|
| |
I filed the .emacs.d "fix speedrun" proposal as a [#C] spec task, with its content preserved in docs/design for spec-create later. The two pearl acks confirmed handoffs I'd already sent, so they needed nothing back.
|
| |
|
|
|
|
| |
Auto-mode sweeps now end with the date, time, and timezone on their own final line, so an away reader gauges each summary's freshness at a glance without computing it. The stamp prints on every sweep, including a quiet "no changes" one — there the stamp is the proof the loop ran.
Same-day addendum to the work-project auto-mode proposal.
|
| |
|
|
|
|
|
|
|
|
| |
Add an auto mode to the triage-intake engine: a self-running variant for when Craig is away but wants tight awareness. It runs the standard sweep on a short interval (default 20 min) as an in-session loop, accumulates findings instead of mutating state, and gates the mutations behind "close the triage" (flush the batch, keep looping) and "stop the triage" (flush, then stop).
A sweep advances nothing — no sentinel write, no todos, no mail actions, no commit. The scan window grows from the last close to the next, so nothing between sweeps is dropped, and the sentinel still means "everything before this timestamp has been scanned" — it just advances once per close. Each sweep reports deltas plus a running "responses awaiting your acknowledgment" list, the primitive an away user needs that a delta-only sweep loses.
The unacked list is durable in .ai/triage-intake-unacked.org so it survives a crash, a clear, or a restart — the away-from-desk case the mode exists for. Delivery is an in-session loop so MCP auth is inherited; a detached cron schedule stays out of scope and belongs to the morning-ops orchestrator, which can reuse this accumulate behavior as its triage limb.
Source proposal from the work project, design decisions ratified 2026-06-15.
|
| |
|
|
|
|
|
|
|
|
| |
Redefine "monitor the inbox" as the explicit behavior Craig wants: run one process-inbox pass now, then loop process-inbox every 15 minutes. The 15-minute loop was previously an opt-in background recipe; it's now the defined meaning of the phrase.
Gate the workflow at both ends on a clean worktree and a green full-suite run. Starting on a dirty tree lets the per-item auto-commit sweep up unrelated changes; starting on a red suite hides whether the monitor broke anything. On a dirty tree, offer to commit in discrete batches; on a red suite, offer to investigate — never start until both are satisfied, and leave the tree clean and green when the loop stops.
Add the no-approvals execute criteria: an accepted item self-applies only when agreed (passed the value gate and Skeptical Review), quick (under ~15 min including verification), and solo (no decision needed from Craig). All three commit and push at the end of the item; miss any and it files or, for shared-asset and convention changes, parks.
Broaden the Skeptical Review to run on every arriving task and file, not only shared-asset proposals — a core right/complete/simpler pass on everything, with the cross-project battery added for changes that sync to consuming projects.
|
| | |
|
| |
|
|
|
|
|
|
| |
helper-mode.org is the canonical home of the helper-instance rules: a second Claude alongside a live primary in the same project. It defines the four read/write tiers (always-safe reads and own-context writes, safe-by-discipline scoped single-heading edits, primary-only file-wide passes and all git mutation, escalation), the four data-integrity windows, the light startup, and the helper wrap-up (archive own context file, skip commit, with the git ban lifting only for an orphaned helper that ends up alone).
protocols.org gets a one-paragraph pointer, and INDEX.org gets a triggerless catalog entry like startup.org, so the no-trigger workflow clears the integrity check without a special case.
The contract is the canonical home. The routing that sends a session here (ai --helper, startup's roster branch, the wrap-up helper branch) ships behind the feature's drill gate and isn't live yet. Until then a session adopts it by an explicit "you are a helper" instruction.
|
| |
|
|
|
|
|
|
| |
agent-roster is the single detection primitive for concurrent same-project Claude sessions: pgrep -x claude, resolve each pid's cwd from /proc, keep those at or inside the project root, and drop the scanner's own ancestry. It exits 0 when alone, 1 when other agents are present (printed pid + cwd), and 2 when the roster can't run. Both the helper launcher and the in-session startup check will call this rather than re-scanning.
pgrep and /proc are the system boundary, so I made them injectable (ROSTER_PGREP, ROSTER_PROC, ROSTER_SELF_PID) and the bats exercise the real include/exclude logic against fixtures, no agents spawned. The unavailable paths (no /proc, or pgrep absent) report on stderr and exit 2 rather than a false "alone".
This is the first slice of the helper-instance task. Startup and ai --helper wiring follow.
|
| |
|
|
|
|
| |
A helper agent's session-context file is .ai/session-context.d/<id>.org. A bare, reused id like "codex" makes the next run resolve to the previous run's leftover anchor, which it then mistakes for a crash to recover or clobbers. That bit on 2026-06-13: a codex run left codex.org for the next session to clean up.
The fix is a convention, not a resolver change. The spawner appends an epoch on the tail (host.project.runtime.<epoch>) so each run gets a fresh anchor. The epoch can't be minted inside session-context-path, since that resolver runs many times per session and must return the same path each call. I documented it in protocols.org, the wrap-up recommended-shape note, and the resolver header.
|
| | |
|
