Borrowing it
Nothing to install: this file belongs to darrenjrobinson/graph-atlas-mcp. 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/darrenjrobinson/graph-atlas-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/darrenjrobinson/graph-atlas-mcpWrote 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/instructions/darrenjrobinson/graph-atlas-mcp/claude-md)<a href="https://agentmods.dev/instructions/darrenjrobinson/graph-atlas-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darrenjrobinson/graph-atlas-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/darrenjrobinson/graph-atlas-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darrenjrobinson/graph-atlas-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01412 | $0.01412 |
| Opus 5.5 | $0.00565 | $0.00565 |
| Sonnet 5.5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
graph-atlas-mcp CLAUDE.md 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 15d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repo
Commits and PRs
- Never add
Co-Authored-By:trailers to commit messages, and never add "Generated with …" attribution lines to PR descriptions. Commit messages end at the last body paragraph. - Branch for changes and open a PR;
mainis merged through review.
Two release channels — do not conflate them
This repo publishes on two independent channels, and confusing them has already caused one production incident:
| Channel | Tag format | Carries | Created by |
|---|---|---|---|
| Data — snapshot database | v2026.08.11 (calendar) |
graph-atlas.db.gz asset |
collect.yml → scripts/create-release.js, daily when changes are detected |
| Server — npm package | v0.3.1 (semver) |
no assets | publish.yml, manually dispatched |
Never use GitHub's /releases/latest (or a bare gh release download) to find the
database. That endpoint returns whichever release published most recently, which is a
semver server release whenever an npm publish lands after that day's data release — and
those carry no database asset. Resolve the newest calendar-tagged release explicitly:
- TypeScript:
fetchLatestDataRelease()insrc/github-releases.ts - Workflows:
gh release list --json tagName --jqfiltered on^v[0-9]{4}\.[0-9]{2}\.[0-9]{2}$
Failing to restore an existing database is not the same as "no database exists yet".
scripts/collect-and-diff.js reads its diff baseline from the committed snapshots/
directory, not from the database, so a run that starts from an empty database still detects
changes and publishes them — releasing a database stripped of all history, permissions,
roles and embeddings over a good one. Fail loudly rather than starting fresh.
This is not hypothetical: every data release from v2026.08.11 to v2026.10.22 shipped
that way, and nothing noticed for ten weeks because the daily workflow never collects
permissions or roles — it only carries them forward through each restore, so once lost they
stay lost. v2026.10.22's asset was replaced with a repaired database on 2026-10-22.
scripts/check-db.js now guards both ends: collect.yml runs it on the restored database,
and create-release.js refuses to publish when permissions, roles, the role map or pre-today
change history are missing.
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.
- 15d ago Changed · +7 lines · +129 tokens per session ea1c7e0dc418
- 2mo ago First seen · 76 lines · 1,283 tokens per session scan A 08423c248698
graph-atlas-mcp CLAUDE.md is an instructions file published in the GitHub repository darrenjrobinson/graph-atlas-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 1,412 tokens to every session, about $0.0056 per session on Opus 5.5. 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.
graph-atlas-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| graph-atlas-mcp CLAUDE.mddarrenjrobinson/graph-atlas-mcp | Instructions file | 1 | yesterday | MIT | A | 1,412 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |