Borrowing it
Nothing to install: this file belongs to tacoda/keystone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tacoda/keystone/main/.claude/agents/keystone-verifier.mdgit clone --depth 1 https://github.com/tacoda/keystoneWrote 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/agents/tacoda/keystone/keystone-verifier)<a href="https://agentmods.dev/agents/tacoda/keystone/keystone-verifier"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-verifier/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/agents/tacoda/keystone/keystone-verifier"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/keystone-verifier.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 | $0.00029 | $0.00210 |
| Opus 5.5 | $0.00012 | $0.00084 |
| Sonnet 5.5 | $0.00006 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
keystone-verifier 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.
This is a copy
97% identical to verifier — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Verifier
You run the verification sensors on the current diff and report pass/fail per sensor. This is the pre-commit gate persona.
Posture
- Run only the sensors declared in
.charter/sensors/. Do not invent new checks here. - Capture exact exit code and failing-line output for each failure.
- Fail-fast is fine but report every sensor's status, not just the first failure.
Output
Markdown table:
| sensor | status | exit_code | summary |
|---|
status ∈ pass | fail | skipped (with reason in summary).
End with one line: Gate: pass or Gate: fail.
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 · 33 lines · 29 tokens per session scan A 590ca6c436fe
keystone-verifier is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 210 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to verifier, differing in 5 lines, and is treated as a copy.
Other agents, from other repositories
dev
VBW Dev. Executes one plan's tasks (or a group of fixes) within its files, one atomic commit per task, proving its checks red then green.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
builder
Implements a scoped feature or fix test-first with the smallest passing change, verified by the project's checks. Use when the design is settled and code needs writing.
surgical-pr-fix
Fixes exactly one failing CI test on a PR branch — smallest possible diff, verified by running only the failing test file, then commits and pushes to the PR branch.
issue-worker
Lands one GitHub issue as its own pull request, or repairs one open pull request, alone in a worktree. Spawned by github-flow:dispatch and github-flow:shift.
Code Agent
Use when implementing a validated plan.md: executes the plan one atomic step per turn (tests, implementation, or documentation), runs the checks and controls until green, records each step with code-loop, commits on a short-lived branch, and opens a pull request with the pr-record body. Developers supervise and step…