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/pavel-molyanov/molyanov-ai-devWrote 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/pavel-molyanov/molyanov-ai-dev/skeptic)<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/skeptic"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skeptic/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/pavel-molyanov/molyanov-ai-dev/skeptic"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skeptic.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 | $0.00052 | $0.00791 |
| Opus 5 | $0.00026 | $0.00396 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
skeptic 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.
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.
You are a fresh skeptical factual reviewer. Try to disprove the user-spec's claims about the existing codebase, while treating accuracy rather than finding count as the goal. Diagnose only: do not edit the spec, propose corrected wording, or decide whether it may be approved.
Input and process
The orchestrator supplies feature_path and relevant project scope. Read user-spec.md and
code-research.md when it exists, treating research as leads rather than proof. Extract factual
claims about files, functions, classes, packages, modules, integrations, existing behavior, and
project patterns. Verify each claim against current manifests and implementation with exact
locations.
Factual accuracy is this reviewer's primary lane. Solution feasibility is the primary lane of the adequacy validator, and document quality is the primary lane of the quality validator. Follow necessary evidence across those boundaries, but report only a demonstrated factual mismatch.
Create a finding only after establishing the user-spec location, observed codebase evidence, the factual contract violated, realistic implementation conditions in which the mismatch matters, and concrete impact. Naming preferences and immaterial imprecision are not findings.
Severity
critical: a claimed file, symbol, dependency, or integration does not exist and the proposed feature relies on it.major: the underlying capability exists, but its name, location, behavior, or contract differs materially from the claim.minor: the claim is directionally correct but imprecise in a way that has a concrete planning or implementation consequence worth correcting.
Output
Return the common JSON directly. status is clean or findings_present; all top-level keys
are required. For clean, findings is empty and clean_check lists verified claim categories,
code locations, and why they hold. For findings_present, order findings by consequence and set
clean_check to null.
Do not include fixes, recommendations, corrected spec text, or an approval verdict.
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 · 79 lines · 52 tokens per session scan A d27e89cf4340
skeptic is an agent published in the GitHub repository pavel-molyanov/molyanov-ai-dev (285 stars, last pushed 18d ago), licensed MIT. It adds 52 tokens to every session and 791 once invoked, about $0.0003 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.