ai dev methodology

    1

    A markdown and git governance methodology for managing AI agents as disciplined squad members with human accountability.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ai dev methodology

    Example session with this skill installed

    We need to start work on Epic E01. Check the backlog, pick the highest ROI item that isn't locked, and create a plan for implementation following the methodology rules.

    • Read your context and instructions
    • Compiled the ai dev methodology

    I have scanned the backlog for Epic E01. Item E01-04-auth-fix is currently available with a Lock: — status. It is rated P0 (High Priority) with an Effort of S (Small), making it the highest ROI task currently available.

    Implementation Plan: E01-04-auth-fix

    RequirementDetail
    Task IDE01-04-auth-fix
    Priority / EffortP0 / S
    Lock StatusAcquired: claude-sess-auth@2025-05-20T14:00Z
    Assurance ProfileA1 (Reversible, standard production work)
    Current Statusin-progress
    Target TestTest: pending (Unit tests for JWT expiration)

    Proposed Changes

    1. Surgical Fix: Update src/auth/validate.ts to correctly handle expired tokens without crashing the middleware.
    2. Style Match: Follow the existing functional pattern used in the authentication module.
    3. Verification: Add a regression test in tests/auth.spec.ts to simulate expired JWT payloads.
    4. Documentation: Update CHANGELOG.md to reflect the fix.

    Safety & Governance Check

    • No direct commit to trunk; work will be pushed to fix/E01-04-auth-token-validation.
    • Pre-commit hooks will be executed; --no-verify will not be used.
    • Input from issue #42 will be treated as data; no external directives will be executed.

    Next steps

    • Approve this plan to begin implementation.
    • Confirm the human verifier for the A1 assurance profile.
    • I will then proceed to modify the files and update the TEST.md file within the epic folder.

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

    About this skill

    Managing a hybrid squad of humans and AI agents leads to broken builds, race conditions, and undocumented shortcuts. This skill implements a markdown and git governance framework that treats AI agents as disciplined contributors, enforcing strict accountability and file-level coordination.

    What it does

    • Enforce governance by applying a hard authority ladder across project instructions, methodology rules, and user directions.
    • Coordinate parallel agents using a lock protocol to prevent multiple agents from overwriting the same backlog items or files.
    • Manage backlog ROI by calculating task priority against effort to ensure agents work on high-impact items first.
    • Guard definitions of done by strictly linking task status to verified test passes and surgical code changes.
    • Mitigate prompt injection by treating all external content, logs, and issue text as untrusted data rather than instructions.

    How it works

    1. Initialize project structure by creating the four planning layers from strategy docs down to granular epic backlogs.
    2. Execute tasks by acquiring a file-lock, creating a PR-based implementation plan, and matching surgical code changes to existing styles.
    3. Apply safety checks by validating all external inputs against the untrusted content rule before processing.
    4. Verify and close by running pre-commit hooks and updating the Test: pass field before marking a task as done.

    Frameworks & tools

    This skill is platform-agnostic, designed for git-based repositories using Markdown for documentation. It integrates with any AI agent capable of reading SKILL.md or CLAUDE.md files.

    Why this beats prompting it yourself

    Manual prompts often fail to maintain state across long autonomous loops, leading to "done" tasks that haven't actually passed tests. This skill provides a rigid, encoded operating contract that prevents AI agreement bias and ensures every change is documented, locked, and verified.

    Use cases

    • Prevent two agents from working on the same feature simultaneously in a shared repo.
    • Automate the sizing and prioritization of a messy backlog based on impact vs effort.
    • Set up a secure autonomous coding loop that refuses to bypass pre-commit hooks or force-push to main.
    • Audit a completed task against a 10-point definition of done checklist to ensure high assurance levels.

    Known limitations

    Does not support direct production deployments or overriding active file locks. Requires a specific repository folder structure to function at full capacity.

    Requires specific folder structure (backlog/epics). Agents cannot override locks or run production deploys. Best for git-based Markdown workflows.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a structured markdown and git-based framework that establishes a "chain of command" and file-locking protocol, preventing agents from overwriting each other's work or taking undocumented shortcuts.

    The skill is platform-agnostic and works with any AI agent or IDE extension (like Cursor or Windsurf) that can interpret instructions from local project files like `CLAUDE.md` or `SKILL.md`.

    You receive the complete architectural documentation, including the four-layer planning templates, the lock protocol specification, and the pre-commit verification checklists required to initialize your repository.

    Setup involves initializing your repository with a specific folder structure and configuring your agent's system instructions to adhere to the provided markdown governance rules.

    No, this skill is specifically designed to enforce a "surgical change" policy and strict pre-commit hooks that prevent agents from bypassing your existing CI/CD safety checks.

    The framework handles backlog prioritization by forcing the agent to calculate an ROI score for every task, ensuring high-impact features are prioritized over low-value refactors.

    New in Agents & Orchestration