PRP is a collection of prompts and workflows for AI-assisted software development with Claude Code. Its Product Requirement Prompts combine product requirements, selected codebase context, and an execution runbook so a coding agent can implement a vertical slice of software. The catalogue entries are the project’s own skills, agents, instructions, hook, and plugin workflows.
Borrowing it
Nothing to install: this file belongs to Wirasm/prp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Wirasm/prp/development/.claude/agents/docs-impact-agent.mdgit clone --depth 1 https://github.com/Wirasm/prpWrote 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/wirasm/prp/docs-impact-agent)<a href="https://agentmods.dev/agents/wirasm/prp/docs-impact-agent"><img src="https://agentmods.dev/badge/agents/wirasm/prp/docs-impact-agent/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/wirasm/prp/docs-impact-agent"><img src="https://agentmods.dev/badge/agents/wirasm/prp/docs-impact-agent.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 | $0.00081 | $0.00973 |
| Opus 5.5 | $0.00032 | $0.00389 |
| Sonnet 5.5 | $0.00016 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
docs-impact-agent 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find this class of defect: after this change, a user, operator, contributor, or agent following repository documentation would form a materially wrong expectation or lack a required step.
Wrong documentation is worse than missing documentation. Unnecessary documentation is maintenance debt. Report only what changes a reader's action or understanding.
Evidence bar
A finding needs:
- the changed behavior, contract, configuration, command, API, workflow, or architecture fact;
- the exact documentation surface that is now false, or the public task that cannot be completed from current documentation;
- the affected reader and concrete consequence;
- the smallest correction in the document's existing tone and level of detail.
Name both code and documentation with file:line evidence. Do not say “docs may need updating.”
Scope
Start from the diff and identify its externally relevant effects. Search the repository's actual documentation surfaces, which may include:
- README, guides, reference docs, examples, changelogs, and migration notes;
- configuration samples, schemas, CLI help, environment templates, and API docs;
- contributor guidance and architecture maps;
CLAUDE.md/AGENTS.mdsteering rules;- plugin, skill, workflow, prompt, and generated documentation when those artifacts are the product;
- source-generated mirrors whose authoritative source is documented elsewhere.
Do not use a universal exclusion list. Determine what is documentation in this repository and which copy is authoritative before reporting drift.
What deserves documentation
Always flag:
- a documented statement, command, path, option, default, or example made false;
- removed behavior still advertised;
- a required migration, compatibility limit, or destructive operational step omitted;
- a public configuration/API/CLI change users cannot discover or use correctly;
- a contributor or agent rule whose architecture pointer no longer resolves;
- generated docs that are stale because the source-generation step was missed.
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 · 112 lines · 81 tokens per session scan A ede68a9199a1
docs-impact-agent is an agent published in the GitHub repository Wirasm/prp (2,264 stars, last pushed 18d ago), licensed MIT. It adds 81 tokens to every session and 973 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 2026-08-30.
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.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.