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 skills add floomhq/moto --skill bouncergit clone --depth 1 https://github.com/floomhq/motoWrote 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/skills/floomhq/moto/bouncer)<a href="https://agentmods.dev/skills/floomhq/moto/bouncer"><img src="https://agentmods.dev/badge/skills/floomhq/moto/bouncer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/floomhq/moto/bouncer"><img src="https://agentmods.dev/badge/skills/floomhq/moto/bouncer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00072 | $0.00511 |
| Opus 5 | $0.00036 | $0.00255 |
| Sonnet 5 | $0.00014 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade C, and why
bouncer scanned grade C 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Any `rm -rf`, `DROP TABLE`, or irreversible operations What it actually says
Bouncer: Pre-flight Risk Check
Before proceeding with any significant action, run this check. The bouncer's job is to catch bad ideas before they become problems.
The Three Questions
-
Is this reversible?
- If yes: proceed carefully
- If no: require explicit confirmation and atomic commit first
-
Is this the right time?
- Are there uncommitted changes that should be committed first?
- Are there tests that should pass first?
- Is there a blocking issue that should be resolved first?
-
Is the scope correct?
- Is the proposed change proportional to the stated problem?
- Are there unintended side effects?
- Is this solving the root cause or a symptom?
Risk Categories
Green (proceed)
- Additive changes (new files, new functions)
- Changes to development/test environments
- Reversible config changes
- Changes with good test coverage
Yellow (proceed with caution)
- Modifying existing logic
- Database schema changes with migration
- Changes affecting multiple consumers
- Production config changes
Red (require explicit confirmation)
- Deleting data or files
- Breaking API changes
- Production deployments without test pass
- Changes to auth or security logic
- Any
rm -rf,DROP TABLE, or irreversible operations
Checklist
Before any significant change:
- Understand what is being changed and why
- Identify all files/systems affected (grep for callers)
- Confirm tests exist or will be written
- Confirm the change is reversible OR have a rollback plan
- For production changes: confirm staging was tested first
Response Format
When invoked, output:
BOUNCER CHECK
Risk level: [GREEN / YELLOW / RED]
Reversible: [YES / NO / PARTIAL]
Preconditions met: [YES / NO - missing: ...]
Recommendation: [PROCEED / PROCEED WITH CAUTION / STOP AND CONFIRM]
Reason: [brief explanation]
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.
- 9d ago First seen · 72 lines · 72 tokens per session scan C 4636f59aa66c
bouncer is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 511 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
self-assessment
Interactive skill assessment with personalized learning path generation.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
investigate
Systematic root-cause debugging: find the cause before writing any fix.