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/claude-mdgit clone --depth 1 https://github.com/Stahl-G/briefloopWrote 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/stahl-g/briefloop/claude-md)<a href="https://agentmods.dev/instructions/stahl-g/briefloop/claude-md"><img src="https://agentmods.dev/badge/instructions/stahl-g/briefloop/claude-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 | $0.01175 | $0.01175 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
briefloop CLAUDE.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 4d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude Code Role
This file is for developing and running BriefLoop inside Claude Code.
For runtime-neutral instructions, see AGENTS.md. The active runtime is the
SQLite-only Codex ControlStore path; the legacy JSON control plane and its
Claude Code writer command (/briefloop) are removed.
First Response In Claude Code
If the user greets you, asks what to do next, or asks how to use BriefLoop from Claude Code, point them to the Codex runtime path first:
briefloop init <workspace> --from-onboarding onboarding.json
briefloop runtime install --workspace <workspace> --runtime codex
briefloop run --workspace <workspace> --runtime codex
Then follow the Store-derived next action:
briefloop runtime next --workspace <workspace>
run returns the current CoreRunNextAction; runtime next / invocation-* /
apply drive the SQLite ControlStore runtime. The legacy five-verb writer
command and /generate-brief delegated workflow are removed.
Standard Claude Code Path
For a real brief workspace:
briefloop onboard
briefloop init <workspace> --from-onboarding onboarding.json
briefloop runtime install --workspace <workspace> --runtime codex
briefloop run --workspace <workspace> --runtime codex
Then operate the run through the Store-derived action:
briefloop runtime next --workspace <workspace>
briefloop runtime invocation-start --workspace <workspace>
briefloop runtime invocation-validate --workspace <workspace> --envelope <path>
briefloop runtime invocation-accept --workspace <workspace> --envelope <path>
briefloop runtime apply --workspace <workspace> --action <path>
For a demo workspace:
briefloop init <workspace> --demo
briefloop run --workspace <workspace> --runtime codex
Repository Development Setup
bash scripts/setup.sh
source .venv/bin/activate
python -m pytest -q
Windows PowerShell:
.\scripts\setup.ps1
.\.venv\Scripts\Activate.ps1
python -m pytest -q
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.
- 4d ago First seen · 181 lines · 1,175 tokens per session scan A 6d93612eb608
briefloop CLAUDE.md is an instructions file published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 6d ago), licensed MIT. It adds 1,175 tokens to every session, about $0.0059 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 2026-08-31.
Other instructions, from other repositories
skills CLAUDE.md
Claude Code instructions for wondelai/skills, covering claude.md, repository purpose, repository structure, current skills (65) and skill file format.
flyto-core AGENTS.md
AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.
autorename-pdf CLAUDE.md
Instructions for ptmrio/autorename-pdf, covering autorename-pdf, development setup, source venv/bin/activate # linux/macos, commands and ai tool integration.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
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.