Borrowing it
Nothing to install: this file belongs to cphoskins/cronometer-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/cphoskins/cronometer-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/cphoskins/cronometer-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/cphoskins/cronometer-mcp/agents-md)<a href="https://agentmods.dev/instructions/cphoskins/cronometer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cphoskins/cronometer-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/cphoskins/cronometer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cphoskins/cronometer-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 | $0.00414 | $0.00414 |
| Opus 5.5 | $0.00166 | $0.00166 |
| Sonnet 5.5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
cronometer-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 today.
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
AGENTS.md
Instructions for coding agents working in this repo.
Releasing
- Always release with
./release.sh <version>. Never bumppyproject.toml,cronometer_mcp/__init__.pyorserver.jsonby hand, and never hand-roll the bump commit, tag or push. The script checks for a clean tree and an unused tag, bumps all three files, commits, tagsv<version>and pushesmainwith tags. - Before running it: the working tree is clean and
python -m pytestpasses. - Before running it: an adversarial Codex review of the unreleased diff has said ship. From Bash:
codex exec -c 'model_reasoning_effort="high"' -s read-only --skip-git-repo-check -o <out.md> "<prompt>" < /dev/null(the< /dev/nullstops it hanging on stdin). Ask it to attack named risks and reproduce, fix real findings with a failing test first, rerun until the verdict is SHIP.codex mcp-serverno longer exists, so there is no MCP tool for this. - Keep pushes to one per release: commit feature work locally without pushing and let
release.shmake the only push (feature commits plus the bump commit and tag). Create the GitHub release withgh release create v<version> --notes-file -; that is an API call, not a push. - The tag alone does not publish. Create a GitHub release from the tag; that triggers
.github/workflows/publish.yml, which publishes to PyPI and then publishesserver.jsonto the MCP Registry (GitHub OIDC, no secrets). Never publish to the registry by hand; if that job fails, re-run it with a manualworkflow_dispatchof the same workflow, which skips PyPI.
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.
- today Changed · +9 lines · +198 tokens per session 854fe11af24a
- 27d ago First seen · 16 lines · 216 tokens per session scan A 63573ebf32aa
cronometer-mcp AGENTS.md is an instructions file published in the GitHub repository cphoskins/cronometer-mcp (27 stars, last pushed today), licensed MIT. It adds 414 tokens to every session, about $0.0017 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 2026-10-04.
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.