agentmods.dev

clawforge AGENTS.md

Repository instructions for ClawForge, a tool that turns YAML scripts into narrated demo videos. It uses Playwright for recording, edge-tts for speech, and ffmpeg for video processing.

In plain words
What is it for?
Use them to run tests and examples, validate or resume video scripts, check dependencies, change output settings, enable verbose logs, or work with the CLI, MCP servers, and SDK.
Why use it?
They explain the available commands, required external programs, entry points, and main processing flow so changes can fit the project correctly.

Instructions file for CodexOpenCode

11 1mo ago A scan 869 tokens original MIT
View the source file Dr-SoloDev/clawforge
Install

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.

agentmods
npx agentmods add instructions/dr-solodev/clawforge/agents-md
Clone the repo
git clone --depth 1 https://github.com/Dr-SoloDev/clawforge

Made for: Codex, OpenCode.

Per session 869 This file is loaded in full into every session.
When invoked 869 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00869 $0.00869
Opus 5 $0.00434 $0.00434
Sonnet 5 $0.00174 $0.00174
Haiku 4.5 $0.00087 $0.00087

Measured 2d ago against content hash 7917e03bd04a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawforge AGENTS.md 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClawForge

Demo videos as code — YAML script → Playwright recording → edge-tts narration → ffmpeg → MP4.

Commands

npm test                          # Run all tests (node --test test/*.test.js)
npm start                         # node bin/clawforge.js
npm run example                   # Run examples/demo-script.yaml
clawforge check-deps              # Verify ffmpeg, ffprobe, edge-tts, Playwright
clawforge validate <script.yaml>  # Validate only, no execution
clawforge resume <checkpoint.json># Resume from .clawforge-checkpoints/
clawforge -o <dir>                # Override output directory
clawforge --verbose               # Verbose logging

External deps

  • ffmpeg + ffprobe in PATH
  • edge-tts Python package (pip install edge-tts)
  • Chromium (npx playwright install chromium)

Entrypoints

Purpose File
CLI bin/clawforge.js
MCP stdio server bin/clawforge-mcp.js
MCP SSE server (port 3100) clawforge-mcp-sse/index.js
Library (npm package) src/sdk-exports.js → exports ClawForgeSDK

Architecture

ClawForgeSDK (events + checkpoint)
  → ProductionSession.run()
    → 1. narrate()      edge-tts → per-scene MP3s
    → 2. record()       Playwright → single MP4
    → 3. compose()      ffmpeg → final MP4 (concat audio, mix music, burn subtitles/overlay)

MCP tools

  • clawforge_produce_video — script path or object, returns {outputPath, stats}
  • clawforge_validate_script — validate without running
  • clawforge_check_dependencies — status of all deps
  • clawforge_dry_run — validate + dep check

Two transports: stdio (npx clawforge-mcp) and SSE (GET /mcp, POST /mcp?sessionId=... on port 3100).

Tests

Uses Node.js built-in test runner. Files: test/smoke.test.js, validator.test.js, errors.test.js, subtitles.test.js, music.test.js, webcam.test.js.

CI (.github/workflows/ci.yml) tests on Node 20.x + 22.x, runs all tests + pipe JSON-RPC through MCP stdio server.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 869 tokens per session scan A 7917e03bd04a

Subscribe to this mod's changes

clawforge AGENTS.md is an instructions file published in the GitHub repository Dr-SoloDev/clawforge (11 stars, last pushed 1mo ago), licensed MIT. It adds 869 tokens to every session, about $0.0043 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.

Browser automationPlanningTesting
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

spring-ai-agentcore AGENTS.md

Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.

spring-ai-community/spring-ai-agentcore · 1,370 tokens

flyto-core CLAUDE.md

Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.

flytohub/flyto-core · 367 tokens

metamask-extension AGENTS.md

AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.

MetaMask/metamask-extension · 14,674 tokens

deckforge AGENTS.md

Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.

tph-kds/deckforge · 498 tokens

fast-browser CLAUDE.md

Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.

m4ttstack/fast-browser · 1,446 tokens