Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Evidence-Gated Dev: Prove It Before You Ship

    1

    A workflow for coding agents: write numbered requirements, plan risk-based tests, lock them, then prove every requirement with tagged test evidence. Includes a guard script that catches skipped or edited tests.

    Free

    Security scanned
    Evidence-Gated Dev: Prove It Before You Ship

    Evidence-Gated Dev: Prove It Before You Ship

    Example session with this skill installed

    I need to add a retry mechanism to the payment gateway. It must retry 3 times on 5xx errors but fail immediately on 4xx. Use a contract-first approach with the Verify mode.

    • Read your context and instructions
    • Compiled the evidence-gated dev

    I have initialized the Evidence-Gated Development workflow in

    Verify mode. I have analyzed the payment gateway requirements and drafted the initial contract and test plan for your approval.

    Requirements Contract & Test Plan

    Contract (R-IDs)

    IDRequirement (Quoted)Kind
    R-1"It must retry 3 times on 5xx errors"Wanted Behavior
    R-2"fail immediately on 4xx"Must Never Happen

    Test Plan (C-IDs)

    IDRisk GroupRequirementDescriptionOracle
    C-1HappyR-2Send 400 Bad Request"fail immediately on 4xx" - expect 1 call total
    C-2DependencyR-1Mock 503 error for 2 calls, then 200"retry 3 times" - expect success on 3rd attempt
    C-3BoundaryR-1Mock 500 error for 5 consecutive calls"retry 3 times" - expect failure after 4 total attempts

    Scope & Protections

    • Allowed Path: src/gateways/payment.js
    • Protected Paths: package.json, vitest.config.ts, tests/setup.ts

    Next steps

    1. Review the requirements and test cases above.
    2. Reply with "Approved" to lock these tests and begin implementation.
    3. Provide the existing payment.js file if not already in context.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    Evidence-Gated Dev makes your coding agent work like a QA-minded team. It writes down what "done" means, plans the tests, locks them, implements, and then proves the result. Anything it could not prove is reported as a warning, never as success.

    Built from the workflow of the open-source AI Department harness and rewritten as plain instructions. No app is required.

    The workflow

    1. Pick a mode. Single is the default; Clarify, Verify or Compare only when a risk signal justifies the extra cost.
    2. Write numbered requirements (R-1, R-2...) quoted from your own words.
    3. Plan test cases across 7 risk groups: happy path, bad data and boundaries, authorization, repeats and concurrency, dependency failures, state transitions, data consistency. You approve the plan.
    4. Write tests tagged [R-x][C-x], then lock them so the agent cannot weaken them to get green.
    5. Implement inside an agreed scope. Lockfiles, configs and CI files stay untouched.
    6. Classify every result as pass, fail, skipped, flaky or incomplete. Missing evidence never counts as verified.
    7. Run an independent review pass. Real bugs become regression tests.
    8. Get an acceptance report listing proof, blockers and warnings.

    Guard script included

    scripts/evidence_guard.py (Python 3, standard library only) checks that:

    • every required requirement has a tagged test
    • no test is skipped, disabled or marked .only
    • approved test files were not modified, deleted or moved

    It makes shortcuts visible. It does not prove your tests are good, and an agent can still skip running it.

    Good for

    Payments and billing, state machines, retries and idempotency, permissions, shared APIs, bugfixes you must prove, refactors of code with weak tests.

    Not worth it for typos, renames or one-line edits. The skill tells the agent to skip the ceremony for those.

    What's inside

    • SKILL.md with the 8-step workflow and hard rules
    • Reference guides: contracts and test cases, verification and findings, modes, scope and budget
    • Templates: task contract and acceptance report
    • The guard script

    Safety

    No network calls and no package installs. The script reads files only under the current folder and writes one file: the lock file you name. Read the source before you run it.

    Limits

    It guides the agent; it cannot force it. Quality depends on the model following the steps. Examples use JS/TS and Vitest, with naming rules for Java, Python and Go.

    Optional companion: the open-source AI Department app (MIT) enforces this workflow in code. See references/ai-department-app.md.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Requires Python 3 for guard scripts. Not for rapid prototyping. Manual intervention needed for system config changes. Final acceptance report requires user review of warnings.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Software
    Git

    Permissions

    Terminal / Shell
    Browser
    Read Files
    Write Files
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The skill provides a specialized system prompt, a library of 'Guard' scripts for Python/Node/Playwright, and a configuration template to manage the SHA-256 file locking and requirement tracing.

    This skill is designed to work with advanced coding agents like Claude 3.5 Sonnet, GPT-4o, and specialized tools like Cursor or Aider that support file-system access and script execution.

    Standard agents often 'move the goalposts' by changing test assertions when their code fails; this skill uses SHA-256 hashing to lock test files, making it impossible for the agent to alter the success criteria without detection.

    The included Python 3 utility script acts as the 'gatekeeper' by scanning your test output and ensuring every requirement ID (R-ID) mentioned in the contract has a corresponding, passing execution trace.

    No, the skill is framework-agnostic and works with any testing tool that generates standard output, including Pytest, Jest, Vitest, and Playwright.

    While powerful, this workflow adds significant 'ceremony' and token overhead; it is optimized for high-stakes business logic and complex state machines rather than simple UI tweaks or rapid prototyping.

    New in Prompt & Skill Engineering

    Free