Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/keithrbennett/cov-loupe/agents-md)<a href="https://agentmods.dev/instructions/keithrbennett/cov-loupe/agents-md"><img src="https://agentmods.dev/badge/instructions/keithrbennett/cov-loupe/agents-md.svg" alt="Measured on agentmods" 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 | $0.03975 | $0.03975 |
| Opus 5 | $0.01988 | $0.01988 |
| Sonnet 5 | $0.00795 | $0.00795 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
cov-loupe 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 6d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md – Codex Cloud Guide
This file provides guidance to Codex, Claude Code (claude.ai/code), Gemini CLI, and any related agents when working with this repository. Treat it as the canonical reference for workflows, tooling, and expectations; update it directly whenever new agent instructions are required.
Mission
- Pull accurate coverage data and project facts for users by driving cov-loupe tools rather than computing it from scratch or analyzing the Simplecov-generated .resultset.json file directly.
- Keep workflow transparent: explain what you did, why it matters, and what the user should consider next.
- Leave the repository tidy; only touch files that advance the request. If you find other opportunities for improvement along the way, mention them in the form of a prompt the user can use later.
Running External Commands
- When running shell commands on this project, use a Bash login shell where possible: run commands via bash -lc '' (or the platform’s equivalent) rather than relying on the default shell.
- If practical, use workdir features of the agent rather than relying on
cdin the command string
Environment & Execution
Prefer project‑local tools and scripts (for example, bin/ scripts, package.json scripts, Makefile targets) instead of ad‑hoc one‑off commands when building, testing, or running the project.
- Prefer
rg/rg --filesfor searches; switch only if ripgrep is unavailable. - Sandbox: workspace write access; network is restricted. Request escalation (
with_escalated_permissions+ short justification) only when indispensable. - Approval mode is
on-request: retry failed-but-needed commands with escalation rather than asking the user manually. - Planning tool: skip for trivial chores; otherwise create a multi-step plan and keep it updated as you work (max one
in_progressstep). - When moving or renaming tracked files, use
git mv(orgit mv -k) instead of plainmvso history stays intact.
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.
- 6d ago First seen · 258 lines · 3,975 tokens per session scan A a21500bcd13a
cov-loupe AGENTS.md is an instructions file published in the GitHub repository keithrbennett/cov-loupe (48 stars, last pushed 1mo ago), licensed MIT. It adds 3,975 tokens to every session, about $0.0199 per session on Opus 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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.