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 skills/tslateman/duet/sweepnpx skills add tslateman/duet --skill sweepgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/sweep)<a href="https://agentmods.dev/skills/tslateman/duet/sweep"><img src="https://agentmods.dev/badge/skills/tslateman/duet/sweep.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 | $0.00017 | $0.00607 |
| Opus 5 | $0.00009 | $0.00303 |
| Sonnet 5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
sweep 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-Op Sweep
Overview
Audit the working tree after agent work completes. Find what the agents left behind.
1. Blast Radius
Map every file touched, across all repos affected:
git diff --stat
git diff --cached --stat
If other repos were modified (check recent tool output or plan files for cross-repo work), run git diff --stat there too.
Flag anything unexpected, files not mentioned in the plan or task.
2. Fixture and Example Damage
Check whether test fixtures, example files, seed data, or sample configs were modified:
- Look for changes to files with names like
example,fixture,seed,sample,mock,test-data - Changes that null out values, remove content, or alter structure are likely test side-effects
- These should almost always be reverted
3. Stale References
Search for references that became outdated by the work:
- Plan files referencing work as "pending" or "TODO" that's now done
- CLAUDE.md / README listing features as planned that are now implemented
- Comments saying "not yet implemented" for code that now exists
- Config or docs pointing to old file paths, function names, or APIs that changed
4. Debug Artifacts
Scan for artifacts agents leave behind:
console.log,print(),echo "DEBUG"statements- Temporary files (
*.tmp,*.bak,/tmp/references) - Commented-out code blocks that serve no purpose
- Test data written to production data directories
5. Scope Bleed
Identify changes outside the task scope:
- Unrelated formatting changes
- Dependency updates not requested
- Refactors beyond what the plan called for
- Changes in other repos' working trees that predate this session
6. Plan Criteria
If plan files exist for the work just completed, check acceptance criteria:
- Read each criterion
- Verify whether it was met (by reading code, not re-running tests)
- Flag any unmet criteria
Report
Present findings as a short checklist:
- Clean, no issues found (say so and stop)
- Fix, items that need correction (damaged fixtures, stale refs, debug artifacts)
- Note, items worth awareness but not blocking (scope bleed, unrelated changes)
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.
- 3d ago First seen · 87 lines · 17 tokens per session scan A 274409de477f
sweep is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 607 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 2026-08-31.
Other skills, from other repositories
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.