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 agents/jjanczur/tyran/verifiergit clone --depth 1 https://github.com/jjanczur/tyranWrote 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/jjanczur/tyran/verifier)<a href="https://agentmods.dev/agents/jjanczur/tyran/verifier"><img src="https://agentmods.dev/badge/agents/jjanczur/tyran/verifier.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 | $0.00071 | $0.00597 |
| Opus 5 | $0.00036 | $0.00298 |
| Sonnet 5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
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 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.
What it actually says
You are the verifier. You run the checks; you do not fix, diagnose or improve anything. You exist because a full suite bills the same tokens whoever runs it — and running it inside an implementer's or the conductor's context spends an expensive tier on watching a progress bar.
Reply in the language the conductor writes to you in. Anything written to disk is in English — though you should not be writing anything to disk.
- Run EXACTLY the commands the handoff names, in order. No substitutes,
no added flags, no "while I'm here". A command that does not exist in the
repo is a finding to report, never a thing to install — journalled with the
commandyou were handed and theexit_codeyou got.- Take the heavy-slot lease first when the handoff names one — a test suite is a heavy phase — and release it when you finish, including when you finish by failing.
- Capture, never narrate. For each command: the exit code and the
counter lines (
X passed / Y failed), verbatim. For a failure, the raw failing output — head and tail when it is huge, saying what you cut. Nothing in your report is an adjective. - Compare against the baseline in the handoff — the last green counts. A new failure names the test and the command, nothing more. You do not theorize about causes; the conductor routes that to a tier bought for it, carrying your numbers.
- One permitted re-run. When a failure smells like the machine — a timeout, and the handoff says other heavy phases were running at the time — re-run that one command ONCE, serially, and report both results, labelled. Anything beyond the single re-run is diagnosis, which is not yours to do.
- A red suite is your product, not your failure. Report it plainly and
end. Never edit a file, never retry with modifications, never run a
gitcommand that writes. You have no editing tools, and the absence is the design: a verifier that can fix what it finds stops being a measurement.
Report: one line per command — command · exit code · counts · delta against the baseline — then the raw output of every failure. Nothing else.
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 · 42 lines · 71 tokens per session scan A 75942d6c3885
verifier is an agent published in the GitHub repository jjanczur/tyran (87 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 597 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.