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/tddnpx skills add stainless-code/codemap --skill tddgit 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 | $0.00032 | $0.00672 |
| Opus 5 | $0.00016 | $0.00336 |
| Sonnet 5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
tdd 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-driven development
Vertical RED→GREEN cycles — one behavior per loop, not horizontal "all tests then all code". Aligns with tracer-bullets and verify-after-each-step.
This repo
- Runner split per
docs/testing-coverage.md:bun test ./src— co-located unit tests (parsers, DB, engines, CLI/MCP handlers). Mock at parser/DB seams.bun run test:golden— indexfixtures/minimal, run SQL scenarios vs committed goldens.bun run test:scripts—scripts/**/*.test.mjs.bun run test:agent-eval— probe/live agent eval harness (after golden index when applicable).
- Co-locate tests next to the module (
src/db.ts→src/db.test.ts). - After each GREEN: format/lint/typecheck per
verify-after-each-step. - Mock at the parser or DB seam (fake
:memory:DB, stub adapter input), never inside the engine under test. SeePATTERNS.md.
Workflow
1. Planning
Confirm behaviors to test (not implementation steps) with the user. Prefer deep modules — small public surface (extractFileData, batchInsert, a recipe handler), complex internals.
2. Tracer bullet (within slice)
RED: one test for first behavior → bun test <file> (or test:golden when recipe/SQL output is the contract)
GREEN: minimal code to pass → re-run
3. Incremental loop
For each behavior: RED → GREEN → run affected tests. One test at a time; no speculative features.
4. Refactor
After GREEN — look for duplication, long methods, shallow modules, feature envy. Run bun test <file> after each step. Never refactor while RED. For production polish on a completed slice, harden-pr lite may run in parallel with tracer-bullet commits.
Checklist per cycle
[ ] Test describes behavior, not implementation
[ ] Test uses the public seam only (parser entry, DB insert path, CLI handler, recipe output)
[ ] Test would survive an internal refactor
[ ] Code is minimal for this test
[ ] bun test (or test:golden / test:scripts) passes on touched file(s)
What ships with it
1 file 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 · 56 lines · 32 tokens per session scan A 8bf221d47570
tdd is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 672 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 2026-08-31.
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…
analyze-usage
Use when asked to analyze codescout tool usage, check for error patterns, audit tool health, generate a usage report, spot anti-patterns, or clear usage statistics to start fresh.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
mcp-headless-test
Run live tests of the Ariadne MCP server using Claude Code in headless mode. Tests tool discovery, invocation, and filtering. Use when validating MCP server changes or checking integration with Claude Code.
mcp-analytics
Check Ariadne MCP tool usage analytics — session counts, tool call stats, durations, and error rates.
release
Prepare a new release of Ariadne packages. Creates changesets, verifies build/tests, and drafts the PR to main.