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/decisiongit 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 | $0.00666 |
| Opus 5 | $0.00005 | $0.00333 |
| Sonnet 5 | $0.00002 | $0.00133 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
decision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- decision — 94% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record and track project decisions as beads issues with structured rationale, alternatives considered, and links to affected work.
Decisions use --type decision. The description field holds the structured decision record.
Record a Decision
When the user wants to record a decision (i.e. the record action of this command):
-
Gather the following (ask if not provided):
- Title: Short summary of what was decided (required)
- Rationale: Why this was chosen (required)
- Alternatives: What else was considered (optional but encouraged)
- Affects: Issue IDs this decision impacts (optional)
- Priority: How important (default P2)
-
Create the issue with structured description:
bd create "<title>" --type decision \
--description "$(cat <<'EOF'
## Decision
<one-sentence summary of what was decided>
## Rationale
<why this was chosen>
## Alternatives Considered
- **<alt 1>**: <why rejected>
- **<alt 2>**: <why rejected>
## Affects
- <issue IDs or area descriptions>
EOF
)"
- If
--affectsissue IDs were provided, link them:
bd dep add <decision-id> <affected-id> --type related
- Show the created decision to the user.
List Decisions
bd list --type decision
To see all decisions including closed/superseded:
bd list --type decision --all
Show a Decision
bd show <decision-id>
Include comments for discussion history:
bd comments <decision-id>
Supersede a Decision
When a decision is replaced by a new one:
- Record the new decision (as above)
- Link the new decision to the old one:
bd dep add <new-id> <old-id> --type related - Add a comment on the old decision:
bd comments add <old-id> "Superseded by <new-id>: <brief reason>" - Close the old decision:
bd close <old-id> --reason "Superseded by <new-id>"
Add Context to an Existing Decision
Use comments to append discussion, implementation notes, or revisit rationale:
bd comments add <decision-id> "Implementation note: ..."
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 · 112 lines · 11 tokens per session scan A 78c0de4a0979
decision 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 666 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.