Fans out a read-only reader per repo over AGENTS.md/ROADMAP.md, folds in the
standards inbox, and synthesizes one priority-grouped to-do list across all
projects (including untriaged inbox items and proposed new projects). Reads and
reports only — prioritizing across projects stays with the user.
Introduce the cross-project capture->triage->roadmap loop: /capture appends an
idea or bug to INBOX.md from any repo (new-project ideas included), /triage drains
a project's items into its AGENTS.md or ROADMAP.md. Give the standards repo its own
AGENTS.md (+ CLAUDE.md symlink) and ROADMAP.md so it follows its own standard, and
add a 'What git tracks' section to portability.md plus the canonical .gitignore
block answering what is committed vs gitignored around .claude and symlinks.
The playbook assumed one canonical chat per project. Add a merge prompt to
Step 1 for reconciling further conversations into the existing AGENTS.md/
ROADMAP.md without overwriting, and note in the retrofit guide that the
"files exist" skip can't mine other chats — that stays manual.
ROADMAP.md was named as a destination in two places but never created,
indexed, or read back. Add the convention to how-i-work.md, note it after
the README decision tree and in the loads-when table, give it a row in the
portability layer table, make the retrofit prompt create it, and have
handoff seed it and pull from it when Current state's next steps run thin.
- Handbook: evaluator/security-auditor are opus/xhigh, not opus/high (matches wrappers).
- portability.md / retrofit-playbook.md: how-i-work.md is ~50 lines, not 'under 50' (it is 52).
- retrofit-playbook.md daily rhythm: close out with /handoff, not the old manual paste, matching README and the handbook.
Read-only documentation drift auditor: checks every README/instruction/HTML claim against the code and reports what no longer matches, modeled on the janitor/reviewer wrappers. Added to the full-eval suite (always-run) and to the subagents handbook roster and length budgets.
Automate the per-project retrofit (git audit, verify, scope, commit,
validate) as a main-thread slash command that asks for the judgment
calls. Step 1 (mining a past chat) stays manual — the command surfaces
which conversation to mine and hands back, since it can't resume one.
Read-only agent that hunts stale, orphaned, and superseded
docs and artifacts and reports removal candidates with evidence.
Scope is docs/artifacts only; never deletes. Adds the guide,
the Claude wrapper, and the handbook roster + length-budget lines.
Read-only subagent that audits a repo against the vendor-neutral /
hot-swap standard: AGENTS.md canonical with a CLAUDE.md symlink, scoped
guides symlinked from .claude/rules with index lines, thin wrappers, and
relative correctly-directed symlinks. Substance in guides/, thin Claude
wrapper in adapters/, catalogued in the subagents handbook.
The brace-bounded grep truncated at the first nested "}" in the usage
object, so the token segment silently rendered empty. Parse each
transcript JSONL line as JSON instead, summing input + cache_read +
cache_creation to match /context's window-occupancy figure.
Show it as "X.Xk/<limit> tokens (Y%)" with the limit auto-sized to the
model's context window (1m vs 200k), and color the segment red once
context reaches 200k.
Top-level index and in-the-moment lookup: the four core documents, the
decision tree for where each instruction goes, what loads when, and the
session rhythm.
Align portability.md with the handoff refactor — every command and
subagent is now a thin wrapper whose substance lives in guides/, with
no self-contained inline exceptions.
Document the portability protocol (vendor-neutral knowledge, vendor-named
symlinks) and a Claude subagents reference handbook, and link the
portability protocol from the retrofit playbook.
Plain-prose guides that the Claude subagent wrappers read and follow:
evaluator, exerciser, researcher, reviewer, security-auditor,
start9-spec-checker, and the full-eval orchestration guide.
Move the Claude command/agent files from claude/ to adapters/claude/ to
match the adapters/<vendor>/ layout, and add the subagent definitions
(evaluator, exerciser, researcher, reviewer, security-auditor,
start9-spec-checker) plus the full-eval command wrapper.
Move the handoff checklist body into guides/handoff.md as plain prose,
and replace the Claude command with a thin wrapper that reads the guide,
matching the full-eval pattern.
Keysat