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 GoogleCloudPlatform/cxas-scrapi --skill cxas-protocol-robust-extractiongit clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapiWrote 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/googlecloudplatform/cxas-scrapi/cxas-protocol-robust-extraction)<a href="https://agentmods.dev/skills/googlecloudplatform/cxas-scrapi/cxas-protocol-robust-extraction"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/cxas-scrapi/cxas-protocol-robust-extraction.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00993 |
| Opus 5 | $0.00028 | $0.00496 |
| Sonnet 5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
cxas-protocol-robust-extraction 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 7d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robust Extraction Protocol
This protocol defines the standard operating procedure for extracting exhaustive requirements (like subintents, CUJs, or logic rules) from large, complex, or fragmented customer artifacts.
It prevents the common LLM pitfalls of "context drift" and "truncation" by enforcing a strict "Divide, Conquer, and Verify" methodology.
General Principles & Anti-Hallucination Guardrails
To ensure 100% coverage and prevent data loss due to tool limits or implicit filtering, follow these principles across all phases:
- Quantify the Scope: Before spawning any subagents or starting extraction, determine the exact total count of target items (files, directories, database rows). Record this number as your "Success Target." You must verify that the sum of items processed equals this target before proceeding to consolidation.
- Coverage over Curation: Default to 100% extraction coverage. Never assume the user only wants the "top" or "most interesting" items unless explicitly instructed to apply a quality filter. A standard or repetitive item is still data that must be reported.
- Circumvent Tool Caps: Be aware that search and listing tools often have display limits (e.g., capped at 50 or 1000 results). If the expected scale (from the Quantify step) exceeds the tool's limit, you must partition the work (e.g., by alphabet or ID range) to ensure no items are hidden by the tool's cap.
- Maintain Traceability: For every extracted requirement or item, record the source file or location it was extracted from. This allows for easy verification and provides context when reviewing the consolidated results.
Core Directives
When tasked with comprehensive extraction or generation from a large corpus, you MUST follow this four-phase methodology:
Phase 1: Parallel Expert Discovery
Never use a single generalist agent or a single prompt to read all files.
- Categorize the input artifacts (e.g., Code/ADK, Diagrams, Test Cases).
- Spawn specialized expert subagents (e.g.,
cxas-ingestor-adk) in parallel, providing each with only the context relevant to their expertise. - Consolidate their initial findings into a centralized list.
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.
- 7d ago First seen · 90 lines · 57 tokens per session scan A 03dc960bf60a
cxas-protocol-robust-extraction is a skill published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (95 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 993 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 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…