CLAUDE.mdA
CLAUDE.md from stephennmiller/taskgraph-ai is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.
mdr add stephennmiller/taskgraph-ai/CLAUDE.md@git:20261101.e3cffdePins git:20261101.e3cffde in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- CLAUDE.md file
- Repository
- stephennmiller/taskgraph-ai
- Path
CLAUDE.md- Versions recorded
- 11
- Latest version
- git:20261101.e3cffde, committed Nov 1, 2026
- First version recorded
- Oct 24, 2026
- Size
- 10,343 bytes
- Repository stars
- 3
- License
- a license file GitHub does not identify
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Claude Code Instructions ## TaskGraph Instructions **Import TaskGraph's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file.** @./.taskgraph/CLAUDE.md This repo's tasks mirror its open GitHub issues (titles end in `(#<n>)`), and the issue wins where they differ. When a PR closes an issue, set its task to `done` in the same PR. See "Roadmap" in `CONTRIBUTING.md`. ## Commands ```bash npm run build # tsdown production build npm run turbo:typecheck # run before pushing npm run typecheck:root # root tsc: scripts/dev.js and evals/, which no workspace covers; CI runs it npm run format-check # Biome; `npm run format` to fix npm run knip # unused files, exports and dependencies; CI runs it npm run test -w @tm/core # one package (also @tm/cli, @tm/mcp); coverage off npm run test:coverage -w @tm/core # coverage and the 80% thresholds; CI runs this; Vitest npm test # root tests/ suite (Vitest, vitest.root.config.ts) npm run evals # real-model plan evals (parse-prd, expand, analyze-complexity); not in CI …
Read the whole file at its exact version.
How to install
mdr add stephennmiller/taskgraph-ai/CLAUDE.md@sha256:1d04053171b0d3e1The line at the top of this page pins the label git:20261101.e3cffde, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_igp4ltt35zjqispk)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between Oct 24, 2026 and Nov 1, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261101.e3cffde latest | 2026-11-01 | e3cffde | 10,343 B | A | view · diff |
| git:20261026.96ee1ae | 2026-10-26 | 96ee1ae | 10,094 B | A | view · diff |
| git:20261026.c883e37 | 2026-10-26 | c883e37 | 10,096 B | A | view · diff |
| git:20261026.6fdee42 | 2026-10-26 | 6fdee42 | 9,988 B | A | view · diff |
| git:20261026.c3a82e9 | 2026-10-26 | c3a82e9 | 9,654 B | A | view · diff |
| git:20261026.854cd80 | 2026-10-26 | 854cd80 | 9,651 B | A | view · diff |
| git:20261025.1488665 | 2026-10-25 | 1488665 | 9,677 B | A | view · diff |
| git:20261024.e8c29f5 | 2026-10-24 | e8c29f5 | 9,567 B | A | view · diff |
| git:20261024.5da64be | 2026-10-24 | 5da64be | 9,563 B | A | view · diff |
| git:20261024.d143583 | 2026-10-24 | d143583 | 9,105 B | A | view · diff |
| git:20261024.b0753a8 | 2026-10-24 | b0753a8 | 8,770 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (10343 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
stephennmiller/taskgraph-ai · 3 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_igp4ltt35zjqispk GET https://markdownregistry.com/api/v1/resolve?ref=stephennmiller/taskgraph-ai/CLAUDE.md GET https://markdownregistry.com/api/v1/blob/1d04053171b0d3e117220fa067cb00f2118260d8cb31a2cddcfd764ce5478464
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.
More from stephennmiller/taskgraph-ai
Every file in stephennmiller/taskgraph-ai