diff options
Diffstat (limited to 'todo.org')
| -rw-r--r-- | todo.org | 22 |
1 files changed, 22 insertions, 0 deletions
@@ -1263,6 +1263,28 @@ Three wins: handoff is one paste not a re-read; forces specs to be implementable If the spec lacks an =Implementation phases= section, the step is the prompt to ask the author to add one before =Ready=. +** TODO [#C] Triage Codex enhancement backlog :spec: +:PROPERTIES: +:CREATED: [2026-05-28 Thu] +:LAST_REVIEWED: 2026-05-28 +:END: + +Codex left a 14-item enhancement backlog for rulesets, filed to [[file:docs/design/2026-05-28-rulesets-enhancement-backlog.org][docs/design/2026-05-28-rulesets-enhancement-backlog.org]]. The doc groups improvements under four goals (agent efficiency, knowledge/effectiveness, token reduction, user experience) and recommends a five-item "highest-impact first" ordering. + +Two of the 14 already have homes and don't need re-filing: +- Item #1 *Runtime-neutral core* = the broader arc captured in =Generic agent runtime support — Codex spec v0= (#16 above). +- Item #2 *Per-agent live session files* = the immediate-correctness slice already filed as [[#16-1 Codex Phase 1][Codex Phase 1 — AI_AGENT_ID + session-context.d/<id>.org]] above ([#B]). + +Triage scope: walk the remaining 12 items, decide for each whether to (a) accept and file as its own TODO with priority + tags, (b) fold into an adjacent existing TODO, (c) defer / park as a someday-maybe, or (d) reject with rationale. The triage output is a one-page disposition table — same shape as a spec-response disposition list — so the decisions land in =git log= and aren't re-litigated. + +Items worth flagging up front: +- Items #3, #4, #6 (workflow routing index, catalog of agent-facing artifacts, install manifest) propose generated machine-readable indices. Compose well as a single =catalog.json= initiative. +- Item #5 (token-tiered files) is a workflow-shape change that touches every existing workflow. Big surface area, real payoff. +- Item #13 (decision log for rulesets itself) overlaps with the existing session-context + docs/design pattern. Worth deciding whether to formalize or keep ad-hoc. +- Items #11 (script interface normalization) and #12 (user-facing command simplification) could land incrementally as scripts and Make targets are touched. + +No implementation before triage. The backlog doc is the canonical reference for the proposals; this task tracks the decision. + ** DONE [#C] Iteration-history backfill for spec-review and spec-response :docs:followup: CLOSED: [2026-05-28 Thu] Source: org-drill inbox 2026-05-28. |