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/gastownhall/beads/auditgit clone --depth 1 https://github.com/gastownhall/beadsWhat 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 | $0.00011 | $0.00256 |
| Opus 5 | $0.00005 | $0.00128 |
| Sonnet 5 | $0.00002 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
audit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- audit — 89% identical, 5 lines differ
What it actually says
Append-only audit logging for agent interactions (prompts, responses, tool calls) in .beads/interactions.jsonl.
Each line is one event. Labeling is done by appending a new "label" event referencing a previous entry.
Usage
-
Record an interaction:
bd audit record --kind llm_call --model "claude-3-5-haiku" --prompt "..." --response "..."bd audit record --kind tool_call --tool-name "go test" --exit-code 1 --error "..." --issue-id bd-42
-
Pipe JSON via stdin:
cat event.json | bd audit record
-
Label an entry:
bd audit label int-a1b2 --label good --reason "Worked perfectly"bd audit label int-a1b2 --label bad --reason "Hallucinated a file path"
Notes
- Audit entries are append-only (no in-place edits).
bd dolt pushincludes.beads/interactions.jsonlin the commit allowlist.
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.
- yesterday First seen · 28 lines · 11 tokens per session scan A bf941ae72f3d
audit is a command published in the GitHub repository gastownhall/beads (26,754 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 256 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
update-changelog-and-tag
You are preparing a release. Follow these steps precisely.
lavra-work-teams
Work on multiple beads with persistent worker teammates that self-organize through a ready queue.
lavra-retro
Weekly retrospective with shipping analytics, team performance, and knowledge synthesis.
lavra-work-ralph
Autonomous retry mode for bead work -- iterates until completion criteria are met or retry budget is exhausted.
lavra-qa
Browser-based QA verification of the running app -- systematic testing from the user's perspective.
lavra-ship
Fully automated ship sequence from code-ready to PR-open with beads closed and knowledge captured.