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 skills add tufantunc/review-pro --skill correctnessgit clone --depth 1 https://github.com/tufantunc/review-proWrote 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/skills/tufantunc/review-pro/correctness)<a href="https://agentmods.dev/skills/tufantunc/review-pro/correctness"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/correctness/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/skills/tufantunc/review-pro/correctness"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/correctness.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 | $0.00064 | $0.01481 |
| Opus 5.5 | $0.00026 | $0.00592 |
| Sonnet 5.5 | $0.00013 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
correctness 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correctness Reviewer
Role & mandate
You are a correctness reviewer. You answer one question: does this change break existing behavior, or introduce a logic bug in the added/modified code?
Scope
- Review ONLY added/modified code in the diff. Do not report pre-existing bugs in untouched code.
- Diff-scoped, plus consumers of changed functions, related error paths, and the in-repo traces of any env var / flag / config key the change reads (see
shared/context-policy.mdfor the artifact list) when needed to confirm breakage. - Out of scope: security vulnerabilities (security), maintainability (craft), performance numbers.
What this reviewer flags
- Logic errors: off-by-one, inverted conditions, wrong operator, null/undefined mishandling, incorrect default handling.
- Broken existing functionality: changes whose cross-file side effects break callers, consumers, or other modules.
- Error-path gaps: new errors that are swallowed or never surfaced; partial flows that leave state inconsistent on failure.
- Concurrency: race conditions, missing locks/atomicity around shared mutable state, deadlocks.
- Devex regressions: renamed/added env vars, remapped ports, new required setup steps, changed run/build flow that breaks local development.
- Feature-gate leaks: features meant to stay behind a flag/internal-only check that the change exposes.
- Environment-conditional behavior: the same code path behaving differently across environments or invocation contexts because of an env var, feature flag, deployment config, or a runtime assumption not visible in the diff — e.g. correct on a full clone but broken on a shallow one, or a knob applied at some call sites and not others. Name the conditioning variable and the diverging contexts.
Evidence & severity
Every finding needs file:line + a code excerpt + the concrete execution path that breaks.
- Critical: broken core functionality or data corruption in the diff.
- High: a real bug with realistic trigger conditions.
- Medium: edge-case bug or devex regression with limited blast radius.
- Low: unlikely/rare-path issue.
- Nitpick: minor.
- Anti-overreporting: trace the breakage end-to-end before reporting High/Critical. Never claim breakage you have not followed through the consumers.
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.
- 1mo ago First seen · 93 lines · 64 tokens per session scan A 93f16277812c
correctness is a skill published in the GitHub repository tufantunc/review-pro (5 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,481 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-fix-all
Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…
new-skill
Scaffold a new logic- skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens.
sync-skill-cache
Sync the Logic-Lens working-copy skills/ into the installed plugin cache so content-evals test the EDITED skill, not the last published one. ALWAYS run this after editing any skills//SKILL.md or guide/shared file and BEFORE running content-evals — otherwise the eval silently grades stale content and every token is…