raven-mcp: Skill for Claude Code

.claude/skills/grab-falsify-loop/SKILL.md

grab-falsify-loop is a skill for Claude Code from rhinocap/raven-mcp. It costs 74 tokens per session (1,276 once invoked), scanned A, original, Apache-2.0.

A testing procedure for changes to a browser overlay in the Raven project. It requires the overlay copies to match and the test suite to pass after each substantive change.

In plain words
What is it for?
Use it when changing the overlay's features, appearance, or behavior, including running tests and checking the result in a browser.
Why use it?
It reduces the chance that a visual change or bug fix breaks the overlay or leaves the two maintained copies inconsistent.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is rhinocap/raven-mcp's own configuration. It tells Claude Code how to work on raven-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything raven-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rhinocap/raven-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rhinocap/raven-mcp/main/.claude/skills/grab-falsify-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rhinocap/raven-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for grab-falsify-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhinocap/raven-mcp/grab-falsify-loop/github.svg)](https://agentmods.dev/skills/rhinocap/raven-mcp/grab-falsify-loop)
Your own site
<a href="https://agentmods.dev/skills/rhinocap/raven-mcp/grab-falsify-loop"><img src="https://agentmods.dev/badge/skills/rhinocap/raven-mcp/grab-falsify-loop/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.

agentmods 80×15 button for grab-falsify-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/rhinocap/raven-mcp/grab-falsify-loop"><img src="https://agentmods.dev/badge/skills/rhinocap/raven-mcp/grab-falsify-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01276
Opus 5 $0.00037 $0.00638
Sonnet 5 $0.00015 $0.00255
Haiku 4.5 $0.00007 $0.00128

Measured 10d ago against content hash 2710703974f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grab-falsify-loop 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 10d 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.

.claude/skills/grab-falsify-loop/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grab overlay falsify loop

Every substantive change to browser/raven-grab.js runs this loop until a falsify wave returns only MINORs or accepted-by-design findings.

Invariants (violations are bugs)

  • Mirror: browser/raven-grab.js must stay byte-identical to web/public/raven-grab.js. After every edit: cp browser/raven-grab.js web/public/raven-grab.js && cmp browser/raven-grab.js web/public/raven-grab.js.
  • Style contract (overlay only): var + function keyword; NO arrow functions, NO optional chaining, NO const/let inside function bodies, NO for...of. Template literals: 23 pre-existing backticks are grandfathered — match the surrounding string-concat idiom, don't add new ones. Nested function declarations ARE used (e.g. commit() in beginStyleEdit). Modern ESM/arrows are fine in test/grab-bridge.test.mjs.
  • Tests: npm test must exit 0 (runs tsc build + node --test test/**/*.test.mjs). The suite honors RAVEN_GRAB_TEST_OVERLAY=<path> to load an alternate overlay copy.
  • isConnected convention: the fake test DOM may leave isConnected undefined — check === false / !== false, never truthiness.
  • buildLayerTree caps: 500 nodes / depth 12.

The loop

  1. Fix/feature leg (codex, agentType: 'codex:codex-rescue'): line-anchored spec per edit; edits ONLY the overlay + mirror. Verify with node --check + targeted node --test.
  2. Test leg (codex, edits ONLY test/grab-bridge.test.mjs): one regression test per behavior. Kill-when-reverted proof is mandatory for fixes: revert the specific fix in a scratch copy, run the test against it via RAVEN_GRAB_TEST_OVERLAY, show it FAILS; then show it passes against the real overlay. A test that can't be killed proves nothing.
  3. Falsify panel (2–3 codex report-only lenses in parallel): prompts start with REPORT ONLY. DO NOT EDIT ANY FILES. Escalate wave-over-wave: single actions → paired/compound gestures → async interleavings (1.5s layer poll, fetch resolutions, setTimeout timers, deactivate/reactivate). Require severity + exact lines + concrete failure scenario + whether an existing test catches it; tell them an empty blocking list is acceptable.
  4. Main-loop disposition: verify EVERY finding against source before accepting — falsifiers over-state (e.g. the template-literal "contract blocker" that was pre-existing convention). Classify: fix now / accepted-by-design (log why) / deferred (log where).
  5. Converge: only MINORs/accepted left → cmp + npm test + eyes-on harness pass → commit with explicit pathspec.

Read the full file on GitHub · 42 lines

Changes

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.

  1. 10d ago First seen · 42 lines · 74 tokens per session scan A 2710703974f2

Subscribe to this mod's changes

grab-falsify-loop is a skill published in the GitHub repository rhinocap/raven-mcp (6 stars, last pushed 17d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,276 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 2026-08-31.

Related

Other skills, from other repositories

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

playwright-cli

A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.

UnicomAI/wanwu · 76 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens