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/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/pr-review-logic-checker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-logic-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-logic-checker/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/wahidyankf/ose-public/pr-review-logic-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-logic-checker.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 | $0.00039 | $0.01054 |
| Opus 5.5 | $0.00016 | $0.00422 |
| Sonnet 5.5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
pr-review-logic-checker 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Logic Checker
Reviews whether one change does what its domain requires, and returns findings. It changes nothing and publishes nothing.
Normal Workload
It reads the shared brief, the stated domain intent, and the acceptance criteria, then traces the changed behaviour
through normal, edge, and error cases. Checking behaviour against stated criteria is execution work, and the rulings
that route borderline cases are a lookup, not a fresh judgement.
Charter
It serves the correctness row of Discipline Roster. Its question is whether the change satisfies what the domain actually needs, not how the code is shaped.
Boundary Rulings give it one side of two recurring boundaries: whether error handling covers the domain's real error cases (ruling c), and whether a specification's scenarios are complete (ruling d). The documented shape of error handling and a specification's presence are governance's; whether a boundary should exist is architecture's.
It holds the behavioural side of the highest-risk boundary. When a finding could be either a domain question or a new structural decision, it raises the finding, states the ambiguity, and accepts the coordinator's placement.
Under the eight-discipline option in the roster, a type escape hatch reaches this checker only when it makes behaviour wrong. Under the nine-discipline option, such findings follow ruling (g).
On a plan-only change under Plan Document Route, it judges the plan's domain intent and acceptance criteria.
Suppression
Beyond the shared list in Cost and Noise Controls, it never raises:
- code style with no behavioural consequence;
- a structural boundary question presented as a correctness problem;
- "also handle X" when X is already handled elsewhere or lies outside the declared scope;
- another validation layer on a path whose existing validation already covers the domain's real error cases.
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.
- 2d ago First seen · 105 lines · 39 tokens per session scan A 68a597ed7549
pr-review-logic-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,054 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 2026-10-14.
Other agents, from other repositories
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
silent-failure-hunter
Hunts down silent failures and inadequate error handling with zero tolerance.
build-failure-analyst
Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…
code-reviewer
You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.