Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/eigenwise/eigenwise-toolshed/update-codebase-mapnpx skills add Eigenwise/eigenwise-toolshed --skill update-codebase-mapgit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00038 | $0.02878 |
| Opus 5 | $0.00019 | $0.01439 |
| Sonnet 5 | $0.00008 | $0.00576 |
| Haiku 4.5 | $0.00004 | $0.00288 |
Grade B, and why
update-codebase-map scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find . -type f -newer .claude/.codebase-info/INDEX.md \ How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Codebase Map
Bring an existing map up to date with surgical edits — detect changes, touch only the affected documents, keep everything internally consistent. This is a refresh, not a full rewrite.
Prerequisite
A .claude/.codebase-info/ directory with INDEX.md must already exist. If it doesn't, stop and
use the map-codebase skill to create the initial map.
Process
Step 1 — Load current state
Read .claude/.codebase-info/.map-state.json to get gitCommit, mappedAt, and the list of
existing documents. Skim INDEX.md to recall what's already covered. (If .map-state.json is
missing — e.g. a map from an older version — fall back to the mappedAt date in INDEX.md, and
plan to write a fresh .map-state.json at the end.)
Step 2 — Detect what changed
Git repo (preferred — precise): diff against the last-mapped commit.
git diff --stat <gitCommit>..HEAD # which files changed, added, deleted
git log --oneline <gitCommit>..HEAD # what the changes were about
git diff <gitCommit>..HEAD -- package.json pyproject.toml go.mod Cargo.toml composer.json Gemfile # dependency churn (adjust to the project's manifests)
No git, or no stored commit (fallback): find source files modified since the map was written.
# files newer than the index (skip noise dirs)
find . -type f -newer .claude/.codebase-info/INDEX.md \
-not -path '*/.git/*' -not -path '*/node_modules/*' -not -path '*/vendor/*' \
-not -path '*/dist/*' -not -path '*/build/*' -not -path '*/target/*' -not -path '*/.venv/*'
Step 2a — Decide whether to hand off
Do not ask the user whether to update the map, run this skill, or create a handoff. Decide using this process, announce the applicable documentation-check outcome, and immediately perform the warranted update or handoff without waiting for a reply.
A true no-op stays inline: report that no documented behavior, structure, interface, dependency, or convention changed, then leave the map alone. Do not create a ticket merely to refresh timestamps or state.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 207 lines · 38 tokens per session scan B f042d49ea467
update-codebase-map is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,878 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…