Borrowing it
Nothing to install: this file belongs to Openly-Useful/project-status. 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/Openly-Useful/project-status/main/CLAUDE.mdgit clone --depth 1 https://github.com/Openly-Useful/project-statusWrote 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/openly-useful/project-status/claude-md)<a href="https://agentmods.dev/instructions/openly-useful/project-status/claude-md"><img src="https://agentmods.dev/badge/instructions/openly-useful/project-status/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/openly-useful/project-status/claude-md"><img src="https://agentmods.dev/badge/instructions/openly-useful/project-status/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 | $0.00516 | $0.00516 |
| Opus 5.5 | $0.00206 | $0.00206 |
| Sonnet 5.5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
project-status 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 2mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude project instructions
Read AGENTS.md and README.md before changing this repository.
Repository boundary
- This repository contains only the Project Status product, canonical skill, generated host wrappers, optional read-only MCP companion, dashboard, tests, and release tooling.
- Do not add owner business records, domain inventories, legal identities, addresses, account information, credentials, local home-directory paths, or unpublished portfolio details.
- Public projections must remain allowlisted and sanitized. Raw internal evidence locators must never be returned from the MCP or browser APIs.
- Do not publish, deploy, install a plugin, create a release, change marketplace state, schedule monitoring, commit, or push unless the owner explicitly authorizes that action.
Canonical paths
- Edit skill behavior only under
skill/project-status. - Regenerate host wrappers with
node scripts/release-sync.mjs sync; do not edit generated wrapper copies directly. - Treat
.project-status/manifest.jsonas the repository-local status source of truth. - The optional MCP companion must remain read-only, self-contained in release archives, and model/host agnostic.
Validation
After relevant changes, run:
node scripts/release-sync.mjs check
node scripts/release-check.mjs --json
npm test
claude plugin validate .claude-plugin/marketplace.json
claude plugin validate plugins/claude/project-status
Release checks distinguish local distribution readiness from public publication readiness. Never describe pending license, third-party notice, publisher, deployment, or marketplace gates as complete without direct evidence.
First-session handoff acceptance
Before continuing work in a newly authenticated Claude session:
- Read this file,
AGENTS.md, andREADME.md. - Run only read-only orientation checks first:
git status --short,git remote -v,claude plugin list,npm run status:validate, andnode scripts/release-check.mjs --json. - Confirm the repository is the public
Openly-Useful/project-statussource and that the installed Project Status plugin is enabled. - Report any drift or failure before editing.
- When the adjacent local business-planning directory is explicitly available, read its
PRIVATE_DATA_POLICY.mdandclaude-continuation.md, but do not open itsprivatesubdirectory unless the owner directly requests a specific private record. - If acceptance passes, summarize the product and privacy state, then continue the guided owner decision queue one question at a time.
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.
- 2mo ago First seen · 43 lines · 516 tokens per session scan A 1c22183c92de
project-status CLAUDE.md is an instructions file published in the GitHub repository Openly-Useful/project-status (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 516 tokens to every session, about $0.0021 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.
project-status CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-status CLAUDE.mdOpenly-Useful/project-status | Instructions file | 0 | 2mo ago | Apache-2.0 | A | 516 | 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 |