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/map-codebasenpx skills add Eigenwise/eigenwise-toolshed --skill map-codebasegit 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 | $0.00040 | $0.03784 |
| Opus 5 | $0.00020 | $0.01892 |
| Sonnet 5 | $0.00008 | $0.00757 |
| Haiku 4.5 | $0.00004 | $0.00378 |
Grade A, and why
map-codebase scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Map Codebase
Generate a codebase map as a collection of atomic documents in .claude/.codebase-info/. Each
document covers one aspect of the project, so the map stays easy to read, update, and navigate. The
map is written for the next Claude session (and the next human): it is grounding context, not
marketing.
Loading is automatic and you don't have to wire anything up: this plugin ships a SessionStart
hook that injects the map at the start of each session, so Claude starts oriented and keeps
consulting and updating it as work goes on. Never edit CLAUDE.md. The hook is the only loading
mechanism; leave CLAUDE.md alone. Your job is just to write the docs in .claude/.codebase-info/.
Output
.claude/.codebase-info/
├── INDEX.md # Navigation hub + how-to-use; the hook injects this at session start
├── architecture.md # System overview, components, boundaries, data flow
├── tech-landscape.md # Languages, frameworks, runtimes, infra, source-of-truth files
├── directory-structure.md # Annotated folder tree
├── entry-points.md # Where execution starts (routes, CLIs, jobs, main files)
├── modules.md # Key modules/packages: purpose, deps, exports
├── communication.md # APIs, events, queues, external integrations (if applicable)
├── database.md # Schema, relationships, migrations (if applicable)
├── dependencies.md # Categorized packages (if applicable)
├── patterns.md # Recurring patterns, error handling, testing, config
├── coding-style.md # Conventions derived from linters + existing code
├── docker.md # Containers / local dev environment (if applicable)
├── onboarding.md # Quick start + common tasks
└── .map-state.json # Machine state (last-mapped commit + date) for staleness checks
This list is a menu, not a checklist. Create only the documents that earn their place in this codebase, and feel free to go beyond the list when a project has a major aspect the standard docs do not cover. Two directions:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 266 lines · 40 tokens per session scan A 8d90d95146d1
map-codebase is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (36 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 3,784 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. 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…