Borrowing it
Nothing to install: this file belongs to SunrisesIllNeverSee/sigrank-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/SunrisesIllNeverSee/sigrank-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/SunrisesIllNeverSee/sigrank-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/sunrisesillneversee/sigrank-mcp/agents-md)<a href="https://agentmods.dev/instructions/sunrisesillneversee/sigrank-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sunrisesillneversee/sigrank-mcp/agents-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/sunrisesillneversee/sigrank-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sunrisesillneversee/sigrank-mcp/agents-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 | $0.02101 | $0.02101 |
| Opus 5.5 | $0.00840 | $0.00840 |
| Sonnet 5.5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
sigrank-mcp AGENTS.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 17d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SigRank MCP — Agent Rules
Quick reference
| What | Command |
|---|---|
| Unit tests | node test.mjs (313 assertions) |
| Signing tests | node --test __tests__/sign.test.mjs |
| Run CLI locally | node index.mjs (TUI if TTY, MCP server if piped) |
| Install deps | npm install |
Bun (faster alternative): All commands work with Bun (~10-30x faster):
| What | Bun command |
|---|---|
| Install deps | bun install |
| Unit tests | bun test.mjs |
| Signing tests | bun test __tests__/sign.test.mjs |
| Run CLI locally | bun index.mjs |
| Run published CLI | bunx sigrank (same as npx sigrank but faster) |
Bun is installed at ~/.bun/bin/bun (v1.3.13). It reads the same package.json
and package-lock.json — no migration needed. Use bunx instead of npx for
one-off package execution.
Publishing
Explicit release only (2026-10-05). .github/workflows/publish.yml never
fires on push-to-main or CI completion. A release happens only via:
- Dispatch release (preferred): Actions → "Publish to npm + MCP Registry"
→ Run with
dry_run=false. The job bumps the patch across all four versioned files (package.json,package-lock.json,server.json,manifest.json), merges the bump PR, runs the full test gate on the merged commit, tags THAT commitv1.0.x, then publishes that exact tree to npm and the MCP Registry. - Manual tag (alternative): push
v1.0.xpointing at a commit whosepackage.jsonalready equals that version — the publish job refuses mismatched tags (ordering invariant: a tag must point at the versioned commit, never the pre-bump tree). - Dry run: dispatch with
dry_run=truevalidates the pipeline without releasing. Registry repair: dispatch withregistry_only=truerepublishesserver.jsonto the MCP Registry after an npm-propagation race.
npm auth is OIDC trusted publishing (no NPM_TOKEN; npm CLI >= 11.5.1
pinned in-workflow). MCP Registry auth is GitHub OIDC. The app auto-syncs
MCP_VERSION by checking npm daily — no dispatch needed.
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.
- 17d ago Changed · +22 lines · +295 tokens per session 5fa1fe34e064
- 1mo ago Changed · +9 tokens per session 6deb016c97dc
- 1mo ago Changed · +87 lines · +723 tokens per session b238cee57301
- 1mo ago First seen · 101 lines · 1,074 tokens per session scan A 0c072e4c2dd0
sigrank-mcp AGENTS.md is an instructions file published in the GitHub repository SunrisesIllNeverSee/sigrank-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 2,101 tokens to every session, about $0.0084 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.