redbar: Instructions file for Codex

AGENTS.md

redbar AGENTS.md is an instructions file for Codex, OpenCode from emersonjds/redbar. It costs 1,456 tokens per session, scanned A, original, MIT.

A project instruction file describing what the redbar codebase does and the rules contributors must follow. Redbar finds test-coverage gaps in changed code by comparing a coverage report with a Git diff.

In plain words
What is it for?
Use it as guidance when developing or reviewing redbar, especially when changing coverage parsing, language support, dependencies, or agent-related code.
Why use it?
It gives coding agents and developers the project context and constraints they need before changing code. It also records restrictions such as having no model calls or runtime dependencies in the analysis code.

Instructions file for CodexOpenCode

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

This is emersonjds/redbar's own configuration. It tells Codex and OpenCode how to work on redbar 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 redbar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to emersonjds/redbar. 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/emersonjds/redbar/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/emersonjds/redbar

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 redbar AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/emersonjds/redbar/agents-md.svg)](https://agentmods.dev/instructions/emersonjds/redbar/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/emersonjds/redbar/agents-md"><img src="https://agentmods.dev/badge/instructions/emersonjds/redbar/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,456 This file is loaded in full into every session.
When invoked 1,456 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 $0.01456 $0.01456
Opus 5 $0.00728 $0.00728
Sonnet 5 $0.00291 $0.00291
Haiku 4.5 $0.00146 $0.00146

Measured 2d ago against content hash 13451c54a2f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

redbar 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 2d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions — redbar

Read by Claude Code, Codex, Cursor, Windsurf and Copilot. CLAUDE.md and .github/copilot-instructions.md point here so there is one source of truth, not five.

What this project is

redbar finds the test-coverage gaps in what a branch changed, and hands them to an agent to fill.

The analysis calls no model. It reads the coverage report the project already produces, crosses it with git diff, and ranks what nothing executes. That is not purism — it is where the number's authority comes from. A wrong number from a model is bad; a wrong number from a regex is worse, because it arrives wearing the compiler's uniform.

The rules that govern every change here

  1. Zero LLM in src/. No AI SDK, no model API call, no agent spawn in the analysis path. CI does not enforce this — you do.
  2. Zero runtime dependencies. dependencies in package.json stays empty. CI fails the build if one appears. The coverage parsers are hand-written on purpose; do not reach for an XML library.
  3. Adding a language is ONE LINE of data in src/languages.ts. If you are about to write switch (lang) or if (lang.id === 'rust') anywhere outside that table, stop — the design has failed and the fix is to move the difference into the registry as data.
  4. Purity. src/coverage/*, src/symbols.ts, src/classify.ts, src/gap.ts never touch disk and never spawn a process. Only detect.ts, git.ts, runner.ts, engine.ts, cli.ts may.
  5. Deterministic output. Same input, same order, byte for byte. A report that reshuffles cannot be diffed in a PR, and the CI gate would flap.
  6. Never install anything into a user's project. init prints the command; the human runs it.
  7. The agent never grades itself. execute is the only command that calls a model. Every verdict it produces except needs-human, timeout, and no-output is measured — by git, by a regex, by the test runner, or by a fresh coverage report. If you are about to let the agent's own output decide whether a gap closed, stop: that is the failure this whole project exists to prevent, reintroduced one layer down.

Read the full file on GitHub · 105 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. 2d ago First seen · 105 lines · 1,456 tokens per session scan A 13451c54a2f6

Subscribe to this mod's changes

redbar AGENTS.md is an instructions file published in the GitHub repository emersonjds/redbar (6 stars, last pushed 2d ago), licensed MIT. It adds 1,456 tokens to every session, about $0.0073 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 2026-09-04.

Related

Other instructions, from other repositories