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 sawy3r/baton --skill baton-verifygit clone --depth 1 https://github.com/sawy3r/batonWrote 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/sawy3r/baton/baton-verify)<a href="https://agentmods.dev/skills/sawy3r/baton/baton-verify"><img src="https://agentmods.dev/badge/skills/sawy3r/baton/baton-verify/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/sawy3r/baton/baton-verify"><img src="https://agentmods.dev/badge/skills/sawy3r/baton/baton-verify.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 | $0.00021 | $0.00665 |
| Opus 5.5 | $0.00008 | $0.00266 |
| Sonnet 5.5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
baton-verify 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the invoking request as input. Resolve relative files from this directory. This standalone skill needs no shared Baton folder.
operation: baton-verify version: baton.operation/v2
Purpose
Independently check finished work against approval.
Inputs
- Work identity, approved plan, exact candidate, and slice Captain decision.
- Required checks, observable evidence, and proof this thread and invocation are permitted and read-only.
Authority
Start threads fresh and separate from delivery roles. Reuse one only for its own
recorded FAIL's direct repair while approved bindings stay unchanged and no
later verdict exists. Keep every invocation read-only; bind its identity, exact
candidate, product identity, and evidence.
Judge the candidate against the approved commitment. Support paths and extra checks are evidence, not scope failures by themselves. They cannot excuse a material behavior, consumed product, contract, or authority change.
Ensure product code, build, test, package, deploy, hooks, and runtime neither
read nor depend on reserved .baton/releases; verify the candidate preserves it
from its exact implementation base.
Actions
- Recheck every trust fact from immutable saved evidence.
- Inspect the exact candidate and full diff; rerun required checks, use helpful extra evidence, and test each acceptance claim where it matters. After repair, recheck the whole candidate and earlier findings.
- For assembly, check every component and whole product.
- Return exactly one verdict:
PASSwhen the exact candidate satisfies the contract;FAILwhen the contract is adequate but candidate or evidence needs correction;BLOCKEDwhen safe progress requires changed behavior, consumed product, authority, contract, or an external decision.
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 · 79 lines · 21 tokens per session scan A 714b3f91b9cb
baton-verify is a skill published in the GitHub repository sawy3r/baton (9 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 665 once invoked, about $0.0001 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 skills, from other repositories
writing-livekit-scenarios
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my…
debugging-livekit-agents
Drives a live multi-turn conversation with a LiveKit agent running locally, using lk agent debugger. Use when the user says "test my agent", "try my agent", "does this work", or "why did it call that tool", after editing an agent to check how it behaves, or when an agent on a speech-to-speech model or one that…
running-livekit-simulations
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and…
ui-regression
This skill should be used when the user asks to "verify UI changes", "audit UI quality", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery…
review-code
Perform a Maestro-style code review with findings ordered by severity and concrete file references.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for AI agents and Agent Skills. Use when initializing eval configurations, running trials, reviewing results, exporting reports, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.