Back to Marketplace

Run this helper free

Answer 3 questions. Get a result in 2 minutes. Preview free.

Start free →
FREE
Scanned
Make Money

openDAG

Use openDAG's contract-first functional DAG workflow for coding-agent work, including master/subagent node implementation, zero-trust file boundaries, verification, and incremental repository conversion into pure typed DAG nodes. Use when an agent is

Install in one line

mfkvault install opendag

Requires the MFKVault CLI. Prefer MCP?

New skill
No reviews yet
New skill
🤖 Claude Code Cursor💻 Codex🦞 OpenClaw
FREE

Free to install — no account needed

Copy the command below and paste into your agent.

Instant access • No coding needed • No account needed

What you get in 5 minutes

  • Full skill code ready to install
  • Works with 4 AI agents
  • Lifetime updates included
SecureBe the first
Ready to run

Run this helper

Answer a few questions and let this helper do the work.

Advanced: use with your AI agent

Description

--- name: opendag description: Use openDAG's contract-first functional DAG workflow for coding-agent work, including master/subagent node implementation, zero-trust file boundaries, verification, and incremental repository conversion into pure typed DAG nodes. Use when an agent is starting a complex implementation, enforcing DAG contracts, assigning or implementing a node, verifying node/file scope, or converting an existing repo toward openDAG. --- # openDAG Use this skill when coding work should follow openDAG: a contract-first, functional DAG workflow with explicit node contracts, tests, allowed file boundaries, and verification. ## Choose The Workflow Use the agent workflow for normal implementation inside an openDAG-aware repo: - Read local instructions and `specs/dag.json` before editing. - Act as master agent unless the user explicitly assigns one node as a subagent. - Define or update contracts and tests before implementation. - Keep deterministic behavior in pure DAG nodes and side effects in thin shell boundaries. - Assign exactly one node and one editable file per subagent when delegation is used. - Verify file scope, node behavior, DAG validity, generated docs, and full project checks before finishing. Detailed reference: `agent/functional-dag-agent.md`. Use the repo-converter workflow when the user asks to retrofit an existing repository: - Scan the requested scope for repo-owned named functions. - Add or update DAG entries for every in-scope function. - Classify deterministic units as pure/helper/orphan and side-effect boundaries as imperative. - Add tests and generated docs before declaring the conversion complete. - For full conversion, continue until no scanner-reported repo-owned functions remain uncovered unless each remainder has a concrete blocker or exclusion. Detailed reference: `repo-converter/functional-dag-repo-converter.md`. ## Core Rules 1. Read repo-local instructions and DAG files before editing. 2. Do not implement a node before its contract and tests exist unless the user explicitly asks for exploratory prototyping. 3. Prefer pure functions with explicit input/output schemas and invariants. 4. Keep filesystem, network, database, process, time, randomness, and framework effects in imperative shell nodes. 5. Track every repo-owned named function, helper, template function, skill artifact, and shell function in `specs/dag.json` when the repo has opted into openDAG. 6. Do not weaken tests to make an implementation pass. 7. Run the repo's DAG validation, node verification, generated-docs check, and full verification before finishing when feasible. ## Bundled Tools - `agent/scripts/check-dag-json.mjs`: lightweight DAG checker for skill-local or early setup use. - `agent/scripts/visualise-dag.mjs`: standalone HTML DAG visualisation generator. - `agent/scripts/scaffold-ts-zod-node.mjs`: TypeScript/Zod node scaffold helper. - `repo-converter/scripts/repo-scan.mjs`: scanner for uncovered functions, side-effect hints, and missing node tests. ## Subagent Boundary When assigning node work, provide exactly one editable file and forbid all other writes. A node subagent may read relevant context but must not change DAG entries, shared contracts, package scripts, public I/O, verification tools, architecture, or another node unless that one file is explicitly assigned. Use `agent/templates/subagent-assignment.md` for assignment packets.

Preview in:

Security Status

Scanned

Passed automated security checks

Time saved
How much time did this skill save you?

Related AI Tools

More Make Money tools you might like

paper-fetch

Free

Use when the user wants to download a paper PDF from a DOI, title, or URL via legal open-access sources. Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, and Semantic Scholar in order. Never uses Sci-Hub or paywall bypass.

Beautiful Prose (Claude Skill)

Free

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

SkillCheck (Free)

Free

Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection,

Design Checker Skill

Free

"Audit designs against 18 professional rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Detects framework automatically, runs code superpowers (aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing), audits for

Vibe Science v7.0 — TRACE

Free

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

Rails Convention Engineer

Free

Rails 8.x application architecture, implementation, and review guidance for production codebases. Use when building or reviewing Ruby on Rails 8 features across models, controllers, routes, Hotwire, jobs, APIs, performance, security, and testing. Tri