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.
git 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/commands/tslateman/duet/probe)<a href="https://agentmods.dev/commands/tslateman/duet/probe"><img src="https://agentmods.dev/badge/commands/tslateman/duet/probe/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/commands/tslateman/duet/probe"><img src="https://agentmods.dev/badge/commands/tslateman/duet/probe.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 | $0.00010 | $0.00375 |
| Opus 5.5 | $0.00004 | $0.00150 |
| Sonnet 5.5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
probe 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 1mo 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
Surface questions worth answering about recent changes. Grounded in actual diffs, not abstract philosophy.
1. Gather Changes
Check what changed recently:
git diff HEAD~3 --stat
git log --oneline -5
If there are uncommitted changes, include those too:
git diff --stat
Read the actual diffs to understand what was written:
git diff HEAD~3
2. Generate Questions
From the diffs and commit history, surface 2-3 questions the developer should answer. Target these categories:
- Design decisions -- Why this approach over alternatives? What tradeoff was made?
- Edge cases -- What inputs, states, or timing would break this?
- Naming and abstraction -- Does the name match what the code actually does? Is the boundary in the right place?
- Assumptions -- What must stay true for this to keep working? What's implicit?
- Missing pieces -- What's conspicuously absent given what was added?
3. Formatting
Present each question as:
Q: [The question]
[1-2 lines of context showing which specific change
prompted this question -- reference files, functions, or lines]
Do not answer the questions. Do not suggest fixes. The value is in the asking.
Keep questions concrete. Name files, functions, variables. Avoid "have you considered..." generality -- point at the code.
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.
- 1mo ago First seen · 66 lines · 10 tokens per session scan A 38af07bc72ae
probe is a command published in the GitHub repository tslateman/duet (1 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 375 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
workday-complete
End-of-day wrap — validate, consolidate, review, changelog.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
worktree
Manage git worktrees for isolated feature development.