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/stainless-code/codemap/ask-agentsnpx skills add stainless-code/codemap --skill ask-agentsgit clone --depth 1 https://github.com/stainless-code/codemapWhat 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 | $0.00026 | $0.00664 |
| Opus 5 | $0.00013 | $0.00332 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
ask-agents 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask agents (router)
Zero context load — you pick the workflow.
The main flow: idea → ship
/grill-with-docs— sharpen the idea; inline updates todocs/(architecture / roadmap / glossary / plans) as decisions land. No codebase yet? Use/grill-me(standalone below).- Branch — multi-session build?
- Yes → capture plan in
docs/plans/<name>.md→ split into GitHub issues. Fresh session per issue. - No → tracer bullets +
tdd+ workflow skills appropriate to this repo in the same window.
- Yes → capture plan in
/harden-pr— lite after each tracer slice; full before PR ready.
Context hygiene
Keep grilling + plan authoring in one window until issues are filed. Each implement session starts fresh from the plan/issue. If the window nears the smart zone, write a compact plan in docs/plans/.
Codebase health (not feature work)
/improve-codebase-architecture— surface deepening opportunities; pick one → back to main flow at grill-with-docs./diagnosing-bugs— hard bugs and perf regressions (model-invoked skill — not a router target).- Periodic hygiene:
/docs-lifecycle-sweepondocs/(model-invoked).
Crossing sessions
/compact— built-in: same session, summarized history — use only at phase breaks.- Fresh session — start from
docs/plans/<name>.mdor the GitHub issue.
Standalone
| Invoke | When |
|---|---|
grill-me |
Sharpen a plan with no codebase (stateless) |
writing-great-skills |
Skill vocabulary + principles |
writing-agents-config |
Codemap repo tier/pairing deltas |
domain-modeling |
Ubiquitous language inline + batch glossary |
tdd |
RED→GREEN tracer-bullet TDD |
verify-after-each-step |
Per-file checks after each milestone |
diagnosing-bugs |
Debug loop for hard bugs |
teach |
Multi-session learning workspace (missions, lessons, retrieval practice) |
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 · 48 lines · 26 tokens per session scan A 340a32f285d1
ask-agents is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 664 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
source-reading
带 AI 精读大型开源仓库，产出每句话都能回溯到源码具体行的书稿、课程或技术文档。核心是零幻觉：每一处引用逐字节核实、行号实读、静默删行由脚本抓出。覆盖锁版本锚点、写逐章大纲、八段结构写章节、编成带封面封底的 HTML 书、机器校验、并行子 Agent 生产六件事。当用户要读懂一个陌生的大型仓库、精读某个开源项目源码、把源码整理成一本书、整理成课程或系列文章、做源码解读、写架构分析、或者要派多个 Agent 并行写技术内容时使用。触发词：精读源码、读源码、源码解读、源码分析、拆解这个项目、这个仓库怎么读、把源码写成课、把源码写成书、写源码精读、架构分析、code walkthrough、带我读代码。.
levelup-specify
Extract Context Directive Records (CDRs) from the current session after completing work. Identifies reusable patterns (rules, personas, examples, evals) and captures directive compliance cases for team-ai-directives.
lane-memory
SMA-style project fact corpus under .agents/memory/. Opt-in via adoc stages.memory.enabled. Use when user says память, lane-memory, corpus, CORE, почему бот забыл, or an agent needs durable non-code facts. Not PROGRESS/LESSONS dumps.
t-doc
Generate project tutorial documentation that reads like a human wrote it, not like AI output. Scans the codebase, extracts architecture/APIs/config/deployment details, and writes structured tutorial docs in the project's documentation target, preferring an existing docs-web site over docs/tutorials/. Use this skill…