Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/stahl-g/briefloop/agents-mdgit clone --depth 1 https://github.com/Stahl-G/briefloopWhat 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 | $0.02496 | $0.02496 |
| Opus 5 | $0.01248 | $0.01248 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
briefloop AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl, PowerShell, Homebrew, and PyPI/archive installs must not rely on an untracked local source repo unless the docs clearly say so. How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
Multi-Agent Brief Workflow is a subagent-first briefing toolkit.
Python CLI commands provide onboarding, workspace setup, runtime handoff, source tooling, validation, audit checks, and final rendering. The selected agent runtime coordinates the brief workflow through handoff artifacts and role-specific agents.
Instruction Scope
This repository contains both development code and runtime agent contracts.
In repository development mode, files under .agents/skills/ are hand-maintained
source assets to inspect, edit, and test. Generated platform adapter assets live
in the packaged Codex runtime kit and docs/agents/. Role instructions become
active only when the active runtime invokes that role.
Use briefloop run --workspace <workspace> --runtime codex to bootstrap the
SQLite ControlStore; the Store, not this repository manual, is the execution contract for a specific brief run.
For BriefLoop operator protocol, use .agents/skills/briefloop/SKILL.md.
Environment Separation
Keep three instruction environments separate:
- Personal Codex environment:
~/.codex/AGENTS.mdis private user-level guidance. Do not copy its personal workflows, private paths, or local preferences into this public repository. - Repository development environment: this
AGENTS.mdguides contributors and coding agents working on the BriefLoop source repo. - End-user brief workspace environment: generated workspaces use
config.yaml,sources.yaml,user.md, runtime handoff artifacts, and role skills. They must not depend on this repositoryAGENTS.mdas their execution contract.
Do not treat repository development instructions as user-facing product behavior. If users need guidance, put it in README, docs, CLI help, generated handoff artifacts, or runtime skills.
Context Mode
Repository development mode
If the current directory contains pyproject.toml, src/, tests/, or scripts/, treat it as the source repository.
Use repository files for development, debugging, tests, generated configs, and documentation updates.
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.
- 2d ago First seen · 221 lines · 2,496 tokens per session scan A 1d9ce50cd17c
briefloop AGENTS.md is an instructions file published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 4d ago), licensed MIT. It adds 2,496 tokens to every session, about $0.0125 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
MCPAudit AGENTS.md
Instructions for saagpatel/MCPAudit, covering agents.md, what this project is, current state, stack and how to run.
goshipit CLAUDE.md
Instructions for Capta1nRaj/goshipit, covering goshipit - project instructions, sync rule (enforce after every change), how to count checks, git commits and package.json description format.
agentlint AGENTS.md
AGENTS.md instructions for agentlint/agentlint, covering agents.md — agentlint, project, build, test, lint, typecheck, architecture and conventions.
sdp CLAUDE.md
Instructions for fall-out-bug/sdp, covering sdp: spec-driven protocol, decision tree, path, try and adopt (prereq: protocol.md | skills | cli).