pr-review-instruction-checker

pr-review-instruction-checker is an agent for Claude Code from wahidyankf/ose-public. It costs 44 tokens per session (1,077 once invoked), scanned A, original, MIT.

A code review agent that checks whether project instructions still describe the repository after a change. It compares changes to tools, dependencies, environments, and pipelines with the instructions given to coding agents.

In plain words
What is it for?
It reviews the current instruction files, checks them against the resulting project setup, and reports missing updates or unnecessary filler.
Why use it?
Instructions can become wrong when the project changes, causing later agents to use outdated commands or assumptions. It also identifies instruction text that adds no enforceable rule.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit It reviews the current instruction files, checks them against the resulting project setup, and reports missing updates or unnecessary filler.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wahidyankf/ose-public/pr-review-instruction-checker
Install

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.

Clone the repo
git clone --depth 1 https://github.com/wahidyankf/ose-public

Made for: Claude Code.

Wrote 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.

agentmods badge for pr-review-instruction-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-instruction-checker/github.svg)](https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-instruction-checker)
Your own site
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-instruction-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-instruction-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.

agentmods 80×15 button for pr-review-instruction-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pr-review-instruction-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pr-review-instruction-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01077
Opus 5.5 $0.00018 $0.00431
Sonnet 5.5 $0.00009 $0.00215
Haiku 4.5 $0.00004 $0.00108

Measured 2d ago against content hash 6cf440e615ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-review-instruction-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.

.agents/agents/pr-review-instruction-checker.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Instruction Checker

Reviews whether the agent instruction files still describe the project one change leaves behind, and returns findings. It changes nothing and publishes nothing.

Normal Workload

It reads the shared brief, lists what the change did to the toolchain, dependencies, environment, and pipeline, and compares that list with what the instruction files tell an agent to do. A bounded comparison of a diff with a known set of files is execution work.

Charter

It owns the instruction currency row of Discipline Roster. Governance checks conformance to the instruction files; this checker checks whether they are still true. Whether a new rule should exist stays with architecture.

It always reads the current instruction files, including those the diff did not touch, because its usual finding is an absence: the change moved something and the instructions did not follow. The files in scope are the canonical instruction body and the sources it imports, per Instruction Body and Vendor Notes.

Filler is instruction text that adds no enforceable rule. Whether an over-long file is also this discipline's finding is the adopter's record beside the roster, measured as Document Word Budget defines.

Suppression

Beyond the shared list in Cost and Noise Controls, it never raises:

  • a toolchain move the instructions already describe at the pinned head, read fresh rather than recalled, since a stale reading proves nothing about decay;
  • how an instruction file is phrased, when nothing in it has gone stale or turned into filler;
  • a one-off change with no effect on how a contributor or agent builds, tests, or runs the project;
  • dense content that carries rules, unless the adopter's record makes an over-limit file this discipline's finding.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 2d ago First seen · 103 lines · 44 tokens per session scan A 6cf440e615ce

Subscribe to this mod's changes

pr-review-instruction-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,077 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.