roster: Instructions file for Claude Code

AGENTS.md

roster AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from mathiasbourgoin/roster. It costs 4,319 tokens per session, scanned A, original, MIT.

A set of project instructions describing Roster's components, repository conventions, file locations, and versioning rules.

In plain words
What is it for?
It is for guiding work on agents, skills, rules, hooks, branches, commits, and releases.
Why use it?
It gives coding agents the local rules they need to make compatible changes in the Roster project.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PreToolUse hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is mathiasbourgoin/roster's own configuration. It tells Claude Code, Codex and OpenCode how to work on roster 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 roster configures →

Reuse

Borrowing it

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

Made for: Claude Code, 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 roster AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mathiasbourgoin/roster/agents-md"><img src="https://agentmods.dev/badge/instructions/mathiasbourgoin/roster/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,319 This file is loaded in full into every session.
When invoked 4,319 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 $0.04319 $0.04319
Opus 5 $0.02159 $0.02159
Sonnet 5 $0.00864 $0.00864
Haiku 4.5 $0.00432 $0.00432

Measured yesterday against content hash 1ce57430dfd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

roster 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 yesterday.

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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — roster

Project

A curated registry of reusable agent definitions, skills, rules, and hooks — paired with a harness builder that assembles shared project harnesses and a recruiter that finds optimal agent teams.

Conventions

  • Commit convention: conventional commits (feat:, fix:, docs:, chore:)
  • Issue tracker: GitHub
  • Branch strategy: feature branches → PR → rebase-merge to main (rebase-only: squash and merge-commits are disabled on this repo)
  • Versioning: semver on each component (version: frontmatter field)
    • Patch (x.x.+1): typo/wording, no behavioral change
    • Minor (x.+1.0): new capabilities, backward compatible
    • Major (+1.0.0): breaking changes (rewritten workflow, renamed tunables)

Component Types

Type Schema Location Install target
Agent schema/agent-schema.md agents/<domain>/ .harness/agents/ then project to .opencode/agents/ or .claude/agents/
Skill schema/skill-schema.md skills/<domain>/ .harness/skills/ then project to .opencode/skills/ or .claude/commands/
Rule schema/rule-schema.md rules/<category>/ .harness/rules/ then project to .opencode/rules/ or .claude/rules/
Tool Hook schema/hook-schema.md hooks/<category>/ .harness/hooks/ then project to runtime settings
Skill Hook schema/hook-schema.md .harness/hooks/skills/<name>/ project-local, auto-discovered by roster-run
KB schema/kb-schema.md kb/ kb/
Harness schema/harness-schema.md .harness/harness.json then project to opencode.json or .claude/harness.json

Shared Harness

  • The canonical project harness lives under .harness/
  • OpenCode compatibility is generated under .opencode/
  • Claude compatibility is generated under .claude/
  • Codex compatibility is generated under .agents/skills/
  • The operational initializer is ./scripts/init-harness.sh <project-root> [profile]
  • The operational projection command is ./scripts/sync-harness.sh <project-root>
  • Agents manipulating installed project harness data should read .harness/harness.json first and treat .opencode/, .claude/, and .agents/ as generated compatibility surfaces

Read the full file on GitHub · 235 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. yesterday First seen · 235 lines · 4,319 tokens per session scan A 1ce57430dfd3

Subscribe to this mod's changes

roster AGENTS.md is an instructions file published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 2d ago), licensed MIT. It adds 4,319 tokens to every session, about $0.0216 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 2026-09-07.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens