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 agentmods add skills/wirasm/prp/prp-debugnpx skills add Wirasm/prp --skill prp-debuggit clone --depth 1 https://github.com/Wirasm/prpWhat 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 | $0.00084 | $0.00852 |
| Opus 5 | $0.00042 | $0.00426 |
| Sonnet 5 | $0.00017 | $0.00170 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
prp-debug 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments:
$ARGUMENTS(and$1,$2, ...) refer to the arguments given when this skill was invoked. Take them from the user's request; if absent, infer them from the conversation.
PRP Debug
Diagnose broken current behavior through the root-cause-analyzer, then make the finding durable in the appropriate GitHub issue. Do not implement the fix.
Input: $ARGUMENTS (if absent, use the conversation).
1. Resolve the report and publication target
Read repository guidance and establish the complete report: symptom, expected behavior, environment, reproduction, logs, and any supplied stack trace.
When the input points to a GitHub issue, read its body, relevant comments, linked issues, duplicates, pull requests, and attachments before diagnosing. Treat the body as historical context, not verified causality.
When no issue is specified, search open issues in the current GitHub repository using the symptom, distinctive errors, affected feature, and likely underlying behavior. Inspect candidate bodies and discussion; title similarity alone is not a duplicate.
- One clear match → use it.
- Several plausible matches → ask the user which issue should own the finding.
- No clear match → plan to create an issue after diagnosis.
If GitHub access or the repository cannot be resolved, complete the diagnosis but stop before publication and state what access is missing. Honor --no-publish or an equivalent explicit request without treating publication as a failure.
2. Run the root-cause analysis
Spawn root-cause-analyzer with the original report, complete tracker context, repository path, and any decisive runtime evidence already available. Do not give it a preferred cause or fix.
Require:
- reproduction at the cheapest authoritative boundary when reasonably possible;
- competing hypotheses and focused falsification;
- a causal chain from observed symptom to the smallest fixable cause;
- the violated invariant and its smallest responsible fix boundary: the existing or missing primitive that should own it, not merely the smallest patch;
- rejected alternatives and explicit uncertainty;
- a regression check that fails before the fix and passes after it.
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 · 61 lines · 84 tokens per session scan A 96f041bc8ab2
prp-debug is a skill published in the GitHub repository Wirasm/prp (2,240 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 852 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…