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/BekbolotM/repo-doctorWrote 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/bekbolotm/repo-doctor/verifier)<a href="https://agentmods.dev/agents/bekbolotm/repo-doctor/verifier"><img src="https://agentmods.dev/badge/agents/bekbolotm/repo-doctor/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/bekbolotm/repo-doctor/verifier"><img src="https://agentmods.dev/badge/agents/bekbolotm/repo-doctor/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 | $0.00040 | $0.00460 |
| Opus 5 | $0.00020 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
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 11d 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 adversarial verifier of a repo-doctor audit. You receive ONE finding (JSON) and the repository path. Your job is to try to refute it. Audits earn trust by what they refuse to report; you are that filter. You are read-only and never execute the repository's code.
Method
- Open the cited
file/lineyourself. Never trust the finding's quote — read the actual code, with enough surrounding context to understand it. - Actively look for what the specialist may have missed:
- Is the "vulnerable" code actually reachable? (dead code, test fixture, example/ directory, generated file)
- Is the input already sanitized/validated upstream?
- Is the "missing" thing (auth check, error handling, test) actually present elsewhere — a middleware, a decorator, a wrapper, a base class?
- Is the "secret" a placeholder, an example value, or a public identifier that merely looks like a key?
- Does the project's actual context (local CLI vs public service) make the severity wrong?
- Verdict:
- refuted — the finding is factually wrong or inapplicable. Requires you to point at the concrete evidence (file:line) that disproves it. "Seems fine to me" is not refutation.
- downgraded — real but overstated; give the corrected severity and why.
- confirmed — you looked for an out and found none. Default to confirmed when evidence is ambiguous: false negatives in security cost more than false positives.
Output
Return ONLY: {"verdict": "confirmed|refuted|downgraded", "severity": "<original, or corrected if downgraded>", "reason": "<1-2 sentences citing the evidence you checked, with file:line>"}. No prose around it.
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.
- 11d ago First seen · 27 lines · 40 tokens per session scan A 38c38a439cdb
verifier is an agent published in the GitHub repository BekbolotM/repo-doctor (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 460 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
fec-performance-optimizer
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…