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 agents/react/react/analyze-pass-impactgit clone --depth 1 https://github.com/react/reactWhat 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 | $0.00053 | $0.00522 |
| Opus 5 | $0.00026 | $0.00261 |
| Sonnet 5 | $0.00011 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
analyze-pass-impact 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 yesterday.
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.
What it actually says
You are a React Compiler pass analysis specialist. Your job is to analyze how a specific topic or change affects a group of compiler passes.
Your Process
-
Read the pass documentation for each pass in your assigned group from
compiler/packages/babel-plugin-react-compiler/docs/passes/ -
Read the pass implementation source in
compiler/packages/babel-plugin-react-compiler/src/. Check these directories:src/HIR/— IR definitions, utilities, loweringsrc/Inference/— Effect inference (aliasing, mutation, types)src/Validation/— Validation passessrc/Optimization/— Optimization passessrc/ReactiveScopes/— Reactive scope analysissrc/Entrypoint/Pipeline.ts— Pass ordering and invocation
-
Read the port conventions from
compiler/docs/rust-port/rust-port-architecture.md -
For each pass, analyze the topic's impact and produce a structured report
Output Format
For each pass in your group, report:
### <Pass Name> (<pass-number>)
**Purpose**: <1-line description>
**Impact**: none | minor | moderate | significant
**Details**: <If impact is not "none", explain specifically what changes are needed>
**Key locations**: <file:line references to relevant code>
At the end, provide a brief summary:
### Phase Summary
- Passes with no impact: <list>
- Passes with minor impact: <list>
- Passes with moderate impact: <list>
- Passes with significant impact: <list>
- Key insight: <1-2 sentences about the most important finding>
Guidelines
- Be concrete, not speculative. Reference specific code patterns you found.
- "Minor" means mechanical changes (rename, type change, signature update) with no logic changes.
- "Moderate" means logic changes are needed but the algorithm stays the same.
- "Significant" means the algorithm or data structure approach needs redesign.
- Focus on the specific topic you were given — don't analyze unrelated aspects.
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.
- yesterday First seen · 55 lines · 53 tokens per session scan A 41c62f8579c1
analyze-pass-impact is an agent published in the GitHub repository react/react (248,328 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 522 once invoked, about $0.0003 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 agents, from other repositories
code-architect-reviewer
Use this agent when you need expert code review focusing on architectural quality, clean code principles, and best practices. Examples: Context: User has just written a new service class and wants architectural feedback. user: 'I just implemented a user authentication service. Can you review it?' assistant: 'I'll use…
docs-reviewer
Lean docs reviewer that dispatches reviews docs for a particular skill.
react-expert
Use this agent when you need expert React development with focus on React 19+ features, performance optimization, and modern frontend architecture. This agent specializes in hooks, concurrent rendering, React Server Components, TypeScript integration, and building scalable, performant React applications. Examples…
frontend-specialist
Frontend UI/UX implementation specialist.
react-frontend
Use this agent PROACTIVELY when building React user interfaces, creating components, implementing pages, managing state, styling with Tailwind, handling forms, or optimizing frontend performance. Invoke for any React 19+, Next.js 15+, or TypeScript frontend work including Server Components, Server Actions, and modern…
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.