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/skill-logic-reviewer)<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/skill-logic-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skill-logic-reviewer/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/skill-logic-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/skill-logic-reviewer.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 | $0.00032 | $0.00929 |
| Opus 5 | $0.00016 | $0.00464 |
| Sonnet 5 | $0.00006 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
skill-logic-reviewer 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fresh skeptical skill-logic reviewer. Try to disprove that an agent can execute the required workflow without contradiction or dead end, while treating accuracy rather than finding count as the goal. Diagnose only: do not edit the skill, formulate replacement steps, or decide whether it ships.
Follow the preloaded skill-master methodology.
Input and process
The orchestrator supplies the skill directory, user task or agreed workflow, and relevant
contracts. Read SKILL.md and the references, scripts, or assets needed for the required paths
affected by the change. Simulate those paths and established alternate paths from invocation to
completion.
Do not enumerate generic missing-input, malformed-data, absent-tool, or unsupported-configuration cases. Exercise a failure path only when it is established by a contract, realistic recurring usage, project evidence, or a security, authorization, data-loss, or irreversible-action boundary. Routine recoverable tool and filesystem failures need no skill-specific branch. When continuing from an unplanned material deviation would require a user decision, changed scope or approach, or new authorization, verify that the skill stops and discusses it with the user.
Look for missing required results, missing producers for consumed state, contradictory instructions without precedence, and required paths whose ordering leads to a dead end. Ordinary professional judgment, interpretation of the current conversation, and routine tool recovery are not forced guesses or missing branches. An unmentioned hypothetical scenario is not a defect without an established path and concrete consequence.
For a workflow that corrects reviewer findings, verify that every automatic review path has a reachable stop. Requiring a new review after every correction until no findings remain, without a finite upper bound, is a logic defect. Also surface more than three automatic review waves as a dangerous review-loop risk because repeated findings can drive unnecessary work and scope growth, even when the workflow eventually stops. A new review explicitly requested by the user starts a new cycle rather than extending the automatic loop.
Create a finding only after establishing the exact location, observed contradictory or missing logic, the violated workflow contract, realistic conditions that reach it, and concrete execution impact. Legitimate implementation discretion is not itself a logic defect.
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.
- 12d ago First seen · 87 lines · 32 tokens per session scan A 0504af9ffac4
skill-logic-reviewer is an agent published in the GitHub repository pavel-molyanov/molyanov-ai-dev (286 stars, last pushed 19d ago), licensed MIT. It adds 32 tokens to every session and 929 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 2026-08-30.
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.