Borrowing it
Nothing to install: this file belongs to KryptosAI/mcp-observatory. 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/KryptosAI/mcp-observatory/main/AGENTS.mdgit clone --depth 1 https://github.com/KryptosAI/mcp-observatoryWrote 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/kryptosai/mcp-observatory/agents-md)<a href="https://agentmods.dev/instructions/kryptosai/mcp-observatory/agents-md"><img src="https://agentmods.dev/badge/instructions/kryptosai/mcp-observatory/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/kryptosai/mcp-observatory/agents-md"><img src="https://agentmods.dev/badge/instructions/kryptosai/mcp-observatory/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 | $0.00708 | $0.00708 |
| Opus 5.5 | $0.00283 | $0.00283 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
mcp-observatory 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide For MCP Observatory
MCP Observatory helps agents test other MCP tools before relying on them. Keep changes focused on trust, compatibility, reports, and real MCP target evidence.
High-Leverage Agent Tasks
- Add a real MCP server target that can run in CI without secrets.
- Follow
docs/target-contribution-guide.mdto add one Safety Index target and generated evidence. - Use
docs/agent-tasks.mdfor copy-pasteable bot and maintainer contribution tasks. - Use
docs/launch.mdanddocs/code-scanning-demo.mdwhen explaining the project to maintainers. - Improve the Markdown or JSON report so autonomous agents can decide whether a tool is safe to use.
- Make startup failure diagnosis clearer.
- Improve
setup-ci --allso maintainers can add read-only MCP checks with less friction. - Add fixtures that prove tool, prompt, resource, schema drift, or security behavior.
Avoid
- generic dashboards
- broad adapter rewrites without a concrete failing target
- marketing-only changes
- CI that requires private credentials by default
- noisy blocking checks before the signal is useful
Useful Commands
npm install
npm ci --prefix hosting
npm run lint
npm run typecheck
npm test
npm run smoke
npm --prefix hosting run check
For a real target sweep:
npm run integration:real
For target-registry contributions:
npm run safety-index
npm test -- tests/safety-index.test.ts
For campaign-attributed launch work:
npx @kryptosai/mcp-observatory test <safe startup command> --campaign agent-ci
npx @kryptosai/mcp-observatory setup-ci --all --command "<safe startup command>" --sarif --campaign agent-ci
Bot Maintainer Contribution Path
If you maintain an autonomous agent, OpenClaw-style productivity system, MCP gateway, or coding-agent runtime, the best contribution is a safe target:
Project:
Safe startup command:
Needs secrets? yes/no
Agent tools/skills that depend on MCP:
What should the agent know before trusting this tool?
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.
- 5d ago Changed · +8 lines · +184 tokens per session 10675b09da6e
- 1mo ago First seen · 82 lines · 524 tokens per session scan A e19ccb4b3d9a
mcp-observatory AGENTS.md is an instructions file published in the GitHub repository KryptosAI/mcp-observatory (135 stars, last pushed 6d ago), licensed MIT. It adds 708 tokens to every session, about $0.0028 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 2026-08-30.
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.