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 drivestream-lab/prayog-skills --skill review-findingsgit clone --depth 1 https://github.com/drivestream-lab/prayog-skillsWrote 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/drivestream-lab/prayog-skills/review-findings)<a href="https://agentmods.dev/skills/drivestream-lab/prayog-skills/review-findings"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/review-findings/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/drivestream-lab/prayog-skills/review-findings"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/review-findings.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 | $0.00096 | $0.03440 |
| Opus 5 | $0.00048 | $0.01720 |
| Sonnet 5 | $0.00019 | $0.00688 |
| Haiku 4.5 | $0.00010 | $0.00344 |
Grade A, and why
review-findings 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 12d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Findings — Interactive Resolution Skill
Purpose
Walks users through findings from audit/validation reports, collects decisions via structured questions, and produces a resolution summary. Works with any skill that generates a findings report — the report file is the interface.
Key principle: This skill does not re-run checks or read source documents. It reads ONE report file and presents its findings interactively. The heavy analysis was already done by the producing skill.
Conventions: prayog-skills/references/id-conventions.md,
prayog-skills/references/artifact-write-contract.md.
When to Use
- After
validate-requirementsgenerates a validation report - After
document-auditgenerates an audit report - When the user wants to systematically work through findings rather than handle them ad-hoc
- When collecting decisions for later batch application to the PRD or integration stubs
Inputs
- Report file path — the findings report to review (REQUIRED). Prefer canonical
prd/reports/Validation-Report-{INIT}.md. - That's it. Everything else is in the report.
Phase 1: Setup
1.1 Read the report file
Read the full report file using the Read tool.
1.2 Detect format
Determine which skill produced the report by checking the heading:
| Heading | Format | Producer |
|---|---|---|
# Requirements Review |
validate-requirements (combined semantic + structural) | validate-requirements skill |
# Requirements Accuracy Review |
validate-requirements (legacy) | validate-requirements skill |
# Document Audit Report |
document-audit | document-audit skill |
| Other | generic | Unknown — use fallback parsing |
1.3 Parse findings by category
Do not treat ## Resolved as open findings. That section records items fixed since a prior report — parse for context only, never walk the user through resolved rows.
validate-requirements format — 4 categories:
| Category | Section header pattern | Severity | Id column | Table Columns |
|---|---|---|---|---|
| Critical | ## Critical |
MUST FIX | VF (or legacy #) |
VF, Type, Location, Target, Check, Finding, Source Says, Doc Claims, Example, Recommendation |
| Should Fix | ## Should Fix |
SHOULD FIX | VF |
VF, Type, Location, Target, Check, Finding, Recommendation |
| Verify | ## Verify |
VERIFY | VF |
VF, Type, Location, Target, Check, Finding, Question for User |
| Gaps | ## Gaps |
GAP | VF |
VF, Type, Location, Target, Check, Finding, Suggested Addition |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 369 lines · 96 tokens per session scan A 1fd44adb22bc
review-findings is a skill published in the GitHub repository drivestream-lab/prayog-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 3,440 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…