From ai-sdlc-harness
Regenerates and stamps the auto-generated repo map the planner uses for codebase navigation. Invoked by user via /repo-map-refresh command.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-sdlc-harness:repo-map-refreshThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The repo map is a navigation aid, never hand-maintained — corrections go
The repo map is a navigation aid, never hand-maintained — corrections go
through regeneration (design.md piece 5B). /init-workspace and
/add-repo both point here for the identical generate-or-regenerate
procedure (step 2 below) — this is the one place it's maintained; don't
fork a second copy of it elsewhere.
${CLAUDE_PLUGIN_ROOT}/bin/harness repo-map-check --repo-name <n> --repo <path> — report
missing / fresh / stale (+ commits behind) to the user.harness-mode: repo-map as
the prompt's FIRST line (the spawn guard regex-matches this exact
header — prose that merely mentions repo-map does not satisfy it; this
is a declared out-of-run spawn, pipeline/surfaces.yaml's
out_of_run_spawns, legal regardless of whether other runs exist in the
workspace) and the repo path. Do not guess the planner's subagent_type
string: check your currently available subagent types for whichever one
corresponds to this plugin's planner (agents/planner.md's frontmatter
name: planner is the identifying detail to match against) —
hooks/guards.py's spawn guard matches on this shape by the LAST
:-segment of whatever string you pass, and a wrong guess doesn't
error, it just silently skips the guard's enforcement (fail-closed
spawn gating, planner's write-confinement to ai//.claude/context/),
which is worse than the guess looking right. The planner can only write
under ai/<run>/ and .claude/context/ (guard-enforced — never repo
source), so point it at .claude/context/repo-map/<name>/. It follows
the map content contract
(${CLAUDE_PLUGIN_ROOT}/skills/dev-workflow/steps/repo-map-task.md):
index.md (purpose/stack/modules/cross-repo edges — intake's targeting
tier), areas/* detail files (each loadable alone), and
conventions.md (observed patterns with cited examples — what
plan-review checks plans against).${CLAUDE_PLUGIN_ROOT}/bin/harness repo-map-stamp --repo-name <n> --repo <path>
— stamping is the orchestrator's job, never the planner's own.npx claudepluginhub mostashraf/ai-sdlc-harness --plugin ai-sdlc-harnessGenerates and incrementally refreshes per-directory codemap.md files so agents get a cheap, always-fresh structure map before exploring. Use to build or refresh repo codemaps; read maps first in exploration-heavy tasks to cut token cost.
Generates a compact repo map (tree + line counts + top-level symbols) and installs a read-the-map-first discipline to cut exploration tokens by ~97%. Use when asked to explore a repo efficiently or stop re-reading the whole codebase.
Creates, refreshes, or validates repo AGENTS.md files using evidence from files, git history, CI to keep them concise and current. Use when missing, stale, or after refactors/tooling changes.