agentmods.dev

agentcov: Instructions file for Codex

AGENTS.md

agentcov AGENTS.md is an instructions file for Codex, OpenCode from trailofbits/agentcov. It costs 2,195 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for agentcov, a tool that records which lines an AI coding agent reads and turns that activity into coverage reports. They explain its code structure, event pipeline, and development practices.

In plain words
What is it for?
Use them when changing agent activity parsing, coverage generation, hooks, command handling, or tests for the agentcov package.
Why use it?
They give an agent the repository context needed to make consistent changes and avoid duplicating fixes across different input sources.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; reads ~/.codex paths.

This is trailofbits/agentcov's own configuration. It tells Codex and OpenCode how to work on agentcov itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentcov configures →

not rated 64repo +3 5d ago A scan 2,195 tokens original Apache-2.0
View source ↗ trailofbits/agentcov
Reuse

Borrowing it

Nothing to install: this file belongs to trailofbits/agentcov. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/trailofbits/agentcov/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/trailofbits/agentcov

Made for: Codex, OpenCode.

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.

agentmods badge for agentcov AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trailofbits/agentcov/agents-md/github.svg)](https://agentmods.dev/instructions/trailofbits/agentcov/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/trailofbits/agentcov/agents-md"><img src="https://agentmods.dev/badge/instructions/trailofbits/agentcov/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.

agentmods 80×15 button for agentcov AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/trailofbits/agentcov/agents-md"><img src="https://agentmods.dev/badge/instructions/trailofbits/agentcov/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,195 This file is loaded in full into every session.
When invoked 2,195 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02195 $0.02195
Opus 5.5 $0.00878 $0.00878
Sonnet 5.5 $0.00439 $0.00439
Haiku 4.5 $0.00219 $0.00219

Measured 2mo ago against content hash 6d4be132bbca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentcov 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 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.

AGENTS.md · 210 lines

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.

AGENTS

Repo Overview

agentcov records which lines of a repository an AI coding agent actually read, then renders that as coverage. The package is agentcov; the repository is trailofbits/agentcov.

There are two ways activity gets in, and they converge immediately:

  • live hooks: Codex calls agentcov hook ... on each tool use
  • backfill: a Codex, Claude Code, or Pi session transcript is replayed after the fact

Both produce the same hook-shaped payload dict, so everything downstream of events_from_payload is shared. When you fix a parsing bug, fix it once in the shared layer rather than per agent.

The pipeline is:

payload -> parser -> CoverageEvent -> .agentcov/events.jsonl
        -> build_coverage -> .agentcov/coverage.json -> lcov / gcov / html / summary

Modules under src/agentcov:

  • cli.py: argparse wiring and command handlers; every subcommand lands here
  • hooks.py: Codex hook install/uninstall, and events_from_payload, the single entry point that turns a payload into CoverageEvents
  • parser.py: shell command parsing (sed, head, tail, cat, awk, sort, pipelines, simple for loops) and rg/grep output parsing
  • models.py: LineRange, ParsedObservation, CoverageEvent, and the identity tuple used for dedupe
  • storage.py: locked append to events.jsonl, atomic coverage.json write
  • aggregate.py: events to per-file/per-line coverage, attribution, and session rollups
  • report.py: LCOV, gcov, self-contained HTML, summary, and unread output
  • config.py: .agentcov.toml loading and exclude matching
  • git.py: repo root discovery, tracked-file inventory, line counts
  • paths.py: path normalization relative to the repo root
  • transcripts.py: locating session JSONL files on disk per agent
  • claude_transcript.py, codex_transcript.py, pi_transcript.py: per-agent transcript record to payload translation
  • backfill.py: orchestrates transcript replay and agent auto-detection
  • importers.py: agent-coverage-style JSON import

Read the full file on GitHub · 210 lines

Changes

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.

  1. 2mo ago First seen · 210 lines · 2,195 tokens per session scan A 6d4be132bbca

Subscribe to this mod's changes

agentcov AGENTS.md is an instructions file published in the GitHub repository trailofbits/agentcov (64 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,195 tokens to every session, about $0.0088 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.

Related

agentcov AGENTS.md compared with instructions from other repositories

agentcov AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentcov AGENTS.mdtrailofbits/agentcovInstructions file645d agoApache-2.0A2,195Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode