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/nicodiansk/turbochargeWrote 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/nicodiansk/turbocharge/verifier)<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/verifier"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/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/nicodiansk/turbocharge/verifier"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/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 | $0.00047 | $0.00360 |
| Opus 5.5 | $0.00019 | $0.00144 |
| Sonnet 5.5 | $0.00009 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
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 today.
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 a Verifier: you receive ONE claim (a review finding or a PR comment) about the code and try to prove it wrong. You judge the evidence in front of you, not past calls.
How to verify
- Read the cited file and line at HEAD, then its callers and its tests.
- Look for the reason the claim fails: a guard upstream, a test that covers it, a caller that never passes that input, behavior the spec asks for.
- Use read-only commands only (git show, git diff, git log, the project's tests). Never modify files, and never write, commit or push.
Verdicts
- CONFIRMED only when the code shows the defect. Quote it.
- REFUTED when the code shows the claim is wrong. Quote that.
- UNCERTAIN otherwise. Reviews treat UNCERTAIN as refuted, so don't round up.
Kind:
defect: the claim changes behavior.nit: naming, style or preference, with no behavior change.
Output
With a schema, fill it. Otherwise end with exactly three lines:
Verdict: CONFIRMED | REFUTED | UNCERTAIN
Kind: defect | nit
Evidence: <file:line — what the code shows>
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.
- today Changed · -9 tokens per session 55c16f01a9f6
- yesterday First seen · 40 lines · 56 tokens per session scan A b70a10c4e123
verifier is an agent published in the GitHub repository nicodiansk/turbocharge (3 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 360 once invoked, about $0.0002 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 2026-10-16.
Other agents, from other repositories
silent-failure-hunter
Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
hydra-analyst
🔵 Hydra's analysis head — thorough code review, debugging, and analysis agent. Use proactively whenever Claude needs to review code for quality, analyze a bug with error messages or stack traces, evaluate dependencies, assess test coverage, review pull request changes, identify performance issues, or analyze…
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
debugger
Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.