Borrowing it
Nothing to install: this file belongs to Ruhan-Wang/Harness_Handbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ruhan-Wang/Harness_Handbook/main/.agents/skills/build-codebase-handbook/SKILL.mdgit clone --depth 1 https://github.com/Ruhan-Wang/Harness_HandbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ruhan-wang/harness_handbook/build-codebase-handbook)<a href="https://agentmods.dev/skills/ruhan-wang/harness_handbook/build-codebase-handbook"><img src="https://agentmods.dev/badge/skills/ruhan-wang/harness_handbook/build-codebase-handbook.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00155 | $0.01885 |
| Opus 5 | $0.00077 | $0.00942 |
| Sonnet 5 | $0.00031 | $0.00377 |
| Haiku 4.5 | $0.00015 | $0.00188 |
Grade A, and why
build-codebase-handbook 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 8d 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.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Codebase Handbook
Create or use a compact source-location index that helps Codex find every place a change touches. Use the active Codex session for analysis; do not call an LLM endpoint, API client, or API-backed generator.
Choose the workflow
Resolve this skill's directory from the selected SKILL.md and call it
HANDBOOK_BUILDER_ROOT.
Choose one mode:
- Task mode: Use an existing generated handbook to route a concrete planning, implementation, debugging, testing, explanation, or review task.
- Build mode: Generate, refresh, or validate a handbook skill.
- Combined mode: Build or refresh the handbook first, then use it for the task.
Do not generate a handbook merely because a normal coding task mentions a repository. Task mode requires an existing handbook or an explicit request to create/use one.
Use an existing handbook for a task
- Resolve the handbook named by the user or already selected by Codex. Otherwise
inspect
<source>/.agents/skills/*-handbook/SKILL.md, excluding this builder. If several match, choose by repository name and described scope; ask only when ambiguity would materially change the task. - Read the generated handbook's
SKILL.mdcompletely. Read itsreferences/overview.md, route throughreferences/index.md, then load only the relevant stage pages andreferences/registers.md. - Inspect
references/coverage.jsonfor freshness of the routed files. When useful, run this builder's validator. Treat validation failures as drift signals, not as permission to skip the user's task. - Read the real source at every cited path and symbol. Search for callers, tests, configuration, and state readers/writers that may have changed since generation.
- Follow the user's requested action boundary:
- For explanation, diagnosis, planning, or review, remain read-only.
- For a requested change, implement it and verify it in proportion to risk.
- For broad changes, use the handbook index and registers as a coverage checklist.
- If the task changes covered source, refresh the handbook only when the user asks to keep it synchronized or repository instructions require it. Otherwise report that its coverage hashes are now stale.
What ships with it
7 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.
- 8d ago First seen · 211 lines · 155 tokens per session scan A b0949fecf4dd
build-codebase-handbook is a skill published in the GitHub repository Ruhan-Wang/Harness_Handbook (327 stars, last pushed 27d ago), licensed Apache-2.0. It adds 155 tokens to every session and 1,885 once invoked, about $0.0008 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…