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 commands/stahl-g/briefloop/init-briefgit 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 | $0.00000 | $0.00270 |
| Opus 5 | $0.00000 | $0.00135 |
| Sonnet 5 | $0.00000 | $0.00054 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
init-brief 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.
What it actually says
Initialize Brief Workspace
Initialize a briefloop workspace using conversational onboarding.
Rules:
- Ask the user at most 4 plain-language business questions.
- Do not use AskUserQuestion for required free-text fields.
- Do not ask the user to edit YAML, JSON, schema, or CLI flags.
- Never ask the user to paste API keys into chat. For live search, explain all options: Tavily, Exa, Brave, Firecrawl, Serper, runtime_websearch, or configure_later. If an API backend is chosen, tell the user to set the key in
.envor shell. - Do not use hidden defaults for required business fields. If the user says "unknown", "default", or "choose for me" for optional fields, choose safe defaults, but keep company, industry/theme, task/title, audience, language, cadence, source style, output style explicit.
- Create
onboarding.jsonin the current working directory. If writing there fails, create.mabw-onboarding/onboarding.jsonand pass that exact path to the CLI. - Run:
briefloop init <workspace-path> --from-onboarding onboarding.json
Show only:
- plain-language setup summary
- created workspace path
- created files
- next command
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 · 25 lines · 0 tokens per session scan A c6713f70acb6
init-brief is a command published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 270 tokens. 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 commands, from other repositories
task
Add a tracked task to the audit manifest — every answer is a flag, and the dialogue only covers what the caller did not pass — move one between phases, or cancel work that will not be done. add allocates the id, initializes all orchestrator fields, updates fileIndex, and revalidates; move renumbers a task into another…
propose
Manage parked phase proposals in the audit manifest — list them, materialize one (or all) into live phases, or drop one. Proposals are parked by /audit:init when the user declines (some of) the synthesized plan; materialization is a move, not a re-synthesis.
report
Produce executive and technical compliance reports.
review
Audit pipeline: re-run Phase sign-off for a phase on demand (e.g. after fixes) — review, test gate, invariant check, optional runtime boot, merge.
phase
Audit pipeline: everything a phase has done to it — add one to a plan that already exists, run it end to end (every ready task, parallel where safe, then sign-off), pin which phase the pipeline reaches for first, or cancel one that will not be done. A bare runs it; --dry-run previews the run without mutating.
ci-triage
Investigate failing GitHub Actions runs and produce root-cause plus Beads follow-up.