Borrowing it
Nothing to install: this file belongs to luis1amaral/system-task-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/luis1amaral/system-task-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/luis1amaral/system-task-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/luis1amaral/system-task-mcp/claude-md)<a href="https://agentmods.dev/instructions/luis1amaral/system-task-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/luis1amaral/system-task-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/luis1amaral/system-task-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/luis1amaral/system-task-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 | $0.00486 | $0.00486 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
system-task-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 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.
What it actually says
system-task-mcp — maintainer notes
MCP server (stdio) + installable Claude Code plugin for System Task. It talks to the public System Task API; there is no private code or credential in this repository.
Rules
- Nothing but the protocol may write to
stdout.stdoutIS the JSON-RPC channel — oneconsole.logcorrupts the message and the client disconnects with an error that points nowhere. Diagnostics go tostderr.scripts/smoke.mjsasserts this. - Only
src/stdio.tsreads the environment; onlysrc/client.tsknows HTTP exists. That is what makes a remote (Worker) transport a new entry point rather than a rewrite of every tool.src/token-store.tsis the one that touches the filesystem — the token cascade (env → file) lives there, andstdio.tsdecides. A remote transport reuses neither: it reads a header. - A new tool goes in
src/registry.ts, and the smoke test's tool count goes up by one — the count is deliberate, so a tool cannot be left out of the registry silently. dist/is committed. Installing a plugin copies the folder and does not runnpm install.- Releasing:
npm run build, then bumpversionin.claude-plugin/plugin.jsononly there (never also inmarketplace.json— the plugin manifest wins and the duplicate just confuses). Without the bump nobody receives the update. - Checks:
npm run check. With a real token:SYSTEM_TASK_TOKEN=stk_... node scripts/smoke.mjs. - Any script that spawns the server passes
SYSTEM_TASK_TOKEN_PERSIST=0(or pointsSYSTEM_TASK_TOKEN_FILEat a temp path). The server stores the token it is given: without this a test's dummy silently replaces the real one in~/.config/system-task/token. - The token never appears in an error message, a log line or an install command.
- Code comments in English, and only when they carry a why the code cannot.
- Record changes in
CHANGELOG.md.
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 · 28 lines · 486 tokens per session scan A f1b7c3e7f796
system-task-mcp CLAUDE.md is an instructions file published in the GitHub repository luis1amaral/system-task-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0019 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.
system-task-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| system-task-mcp CLAUDE.mdluis1amaral/system-task-mcp | Instructions file | 0 | 2mo ago | MIT | A | 486 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |