Claude Code skills, rules, and language bundles https://git.cjennings.net/rulesets/atom?h=main 2026-07-20T21:47:39+00:00 2026-07-20T21:47:39+00:00 Craig Jennings c@cjennings.net 2026-07-20T21:47:39+00:00 urn:sha1:61454894349e75b593ede5901a7b348ad580d3ce "page me" and "text me" now name distinct channels: page is the desktop notification, text is the Signal phone push, and "text and page me" fires both. Before, "page me" defaulted to desktop and the phone was an unnamed "on my phone" variant, so you couldn't name the phone without naming the machine. I renamed the Signal tool agent-page to agent-text to match, with a deprecated agent-page shim delegating to it so callers and other machines don't break before their next install. The dispatch and tests are otherwise unchanged. I rewrote protocols.org "Reaching Craig", page-me.org, and work-the-backlog's away-run logic around the three phrasings, and updated the runbook. 2026-07-20T21:03:08+00:00 Craig Jennings c@cjennings.net 2026-07-20T21:03:08+00:00 urn:sha1:302b062680c8fbd9743d4e083154ac5fc314955a The pager worked but was undocumented and drifting stale: signal-cli warned the account had gone 47 days without a receive, and no runbook existed to hand a future session or a non-Claude runtime. I added the runbook under docs/design/ and a roam-sync-shaped receive timer that drains the queue every 15 minutes, keeping the account warm and surfacing reply messages. I also generalized agent-page: it now sends directly from any machine holding the pager account and relays to velox only when it doesn't. ratio is linked as a device of the account, so a page lands even when velox is down. The receive script no-ops cleanly where the account isn't registered, since the units stow onto every machine via the shared common package. 2026-07-20T13:52:48+00:00 Craig Jennings c@cjennings.net 2026-07-20T13:52:48+00:00 urn:sha1:93a2e6dd2968e46e77704e01123a836a5cc1513b The autonomous-batch spec's three source artifacts (the Phase E proposal, its diff, the sender note) moved from working/inbox-zero-phase-e/ into docs/design/ under dated names, with the spec's inbound links repointed. The spec is IMPLEMENTED, so the working dir was a filing candidate. Also removed the spent working/sentry-2026-07-19-working-files-ruling/ staging dir, whose proposal shipped in the working/-tracked-from-creation change. working/ is now empty and gone. 2026-07-20T13:49:52+00:00 Craig Jennings c@cjennings.net 2026-07-20T13:49:52+00:00 urn:sha1:70fbe011394523595974be311667db63425072ed Three pointed at artifacts that were folded in or processed away (a spec-review file merged into wrapup-routing-spec, a removed pearl inbox note, a home-side subprojects log with no rulesets file) — delinked to plain text so the reference survives without a dead link. The fourth repoints the autonomous-batch spec at inbox.org, since inbox-zero.org was renamed in the consolidation. Surfaced by the sentry link-integrity pass. 2026-07-19T00:55:43+00:00 Craig Jennings c@cjennings.net 2026-07-19T00:55:43+00:00 urn:sha1:bc1d81d835237343a4ced82a9025f2dc34f45865 Filed as [#B] work items with their origin proposals preserved under docs/design/: the todo-cleanup dated-seal archiving model, the dated-log planning-line strip plus its lint backstop, a hook to enforce the task-boundary inbox check, and home's colloquialisms / "the list" before-close-queue convention. The first two both touch todo-cleanup.el and are cross-linked to build as one batch. The last two carry the design worked out this session so they start warm. 2026-07-16T18:42:53+00:00 Craig Jennings c@cjennings.net 2026-07-16T18:42:53+00:00 urn:sha1:c98fda556e9211573dab3e32eaa5c42c2dedbfcb Installing a second language bundle into a project silently replaced the first one's config. settings.json and githooks are copied with cp -rT (always overwrite), so installing bash over elisp rewired the validate hook to validate-bash.sh and dropped check-parens from pre-commit, leaving validate-el.sh orphaned on disk. The output said [ok] for both. A project could lose its paren check or secret scan and read the install as success. The guard detects which bundles a project already has, by the same rule fingerprint sync-language-bundle uses, and refuses when the incoming bundle would overwrite a file another one ships. It names each file at risk. FORCE=1 still overrides, and the message says that also re-seeds CLAUDE.md, which is destructive on a customized project. Only three of the five shared filenames actually collide. gitignore-add.txt is appended and deduped, and CLAUDE.md is seed-only, so both compose across bundles already. This doesn't decide whether polyglot projects are supported, and the guard shouldn't be read as "no". A non-overlapping pair still installs: bash ships settings.json and githooks with no coverage fragment, python ships only a coverage fragment, so the two compose today. The real line is overlap, not polyglot, and nothing chose it. The open question, along with the identical coverage target names both fragments define, is filed. home reported this after scaffolding clock-panel with python and typescript, which hit the coverage fragment. The settings.json and githooks cases are worse and hadn't been noticed. No project was damaged: the three bundles that collide aren't doubled up anywhere. 2026-07-16T18:24:24+00:00 Craig Jennings c@cjennings.net 2026-07-16T18:24:24+00:00 urn:sha1:125c1e9777d66645cf23b30b3d2de1c91fb492aa home proposed promoting its subproject pattern (a folded-in standalone project living as a self-contained subdir under a parent's scope) into the rules layer. The pattern reads as sound. I deferred it on evidence rather than merit, and preserved both the proposal and home's worked instance here so the decision has its source. Two findings drove the deferral. It's N=1: across all 27 agent scopes, home is the only project with subprojects, and all nine came from one fold. There's no second instance to say which parts are general and which are home-shaped. The placement also contradicts the proposal's own argument. Rules load into every session of every project, and the doc argues that layer is a tax paid whether or not it's relevant, with depth belonging one open away. At 282 lines it would be the third-largest rule and add ~11% to the layer, so every unrelated project would carry a one-project convention. I want to scout which projects would actually get subprojects, and why, before shaping anything. That evidence decides whether the pattern gets dropped or adjusted. Two things to fix if it ever promotes: the doc cites a privacy-model rule that doesn't exist (the real content is the gitignore-vs-track and public-reachability decision), and about half of it is home's instance rather than rule content. 2026-07-14T07:50:17+00:00 Craig Jennings c@cjennings.net 2026-07-14T07:50:17+00:00 urn:sha1:f14dd8798842dda026d2613791d77f44c258ade7 Spec for the overnight hygiene supervisor: ten serialized passes, mkdir-atomic locks with heartbeat under the runtime dir, a host-suffixed unpushed branch, interactive entry gates with no report-only mode, and roam-sync kept as the roam repo's only committer. All 10 decisions and 12 adversarial-review findings are resolved in the file; status stays DRAFT pending a deep read. The build task and three deferrals are filed. 2026-07-13T21:42:32+00:00 Craig Jennings c@cjennings.net 2026-07-13T21:42:32+00:00 urn:sha1:3ef55807a23f7dd447ecf9fc34d6512fb3893d6b session-context-path already carries a runtime segment, the anchor cycle is plain files, and self-inject is harness-agnostic with only its payload Claude-shaped. A codex auto-flush is a documented payload variant whose second injected line carries the resume instruction, replacing the SessionStart hook. Wire it when a codex session first wants it. 2026-07-13T19:54:03+00:00 Craig Jennings c@cjennings.net 2026-07-13T19:54:03+00:00 urn:sha1:0ee94abca7dde8356709d712b2dbf735b029f2b8 All 29 skill and command bodies are markdown, so a single sentence in the future non-Claude entry file (a /name reference resolves to the skill or command file, read and follow it) carries the whole library. Auto-invocation degrades to by-name, which the publish flow already uses. flush stays Claude-only, owned by the session-plumbing child.