More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Lean Execution: Verified, No-Fluff Agent Output

    1

    Generic "be concise" prompts make it worse: agents start skipping tests and hiding uncertainty.

    $4

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Lean Execution: Verified, No-Fluff Agent Output

    Lean Execution: Verified, No-Fluff Agent Output

    Example session with this skill installed

    CI is red on main. Fix it.

    • Read your context and instructions
    • Compiled the lean execution

    Summary

    Illustrative session. The agent jumps to the first failing CI step, reproduces it locally, fixes the root cause (no test disabled) and reports in four lines.

    What the agent did (no narration shown to the user)

    StepAction
    InspectRead only the first failing step of the CI log and its stack trace
    ReproduceRan npm run test:e2e -- checkout locally: same failure
    Diagnosecheckout.spec.ts used a hard-coded date that has now expired
    FixReplaced the hard-coded date with a fixed test clock
    VerifyRe-ran the failing step locally: pass

    Report delivered

    DONE: Fixed checkout.e2e — expired hard-coded date replaced by a fixed clock (tests/e2e/checkout.spec.ts:14).
    VERIFIED: npm run test:e2e -- checkout (local) — pass. CI re-run not triggered from here.
    BLOCKED: NONE
    NEXT: Push to re-run CI.
    

    What it did NOT do

    • Paste the 900-line CI log
    • Announce a plan or narrate each command
    • Disable the failing test to turn CI green
    • Ask "should I continue?"

    Next steps

    1. Push the branch to re-run the pipeline.
    2. Run the included evals/tasks/04-failing-ci.md checklist on your own repo to compare runs with and without the skill.

    File names, commands and results in this demo are illustrative.

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

    About this skill

    Coding agents spend a large share of their output on things you did not ask for: restating your prompt, announcing obvious plans, narrating every tool call, reading whole files for one line, recapping finished work and asking "should I continue?". Generic "be concise" prompts make it worse: agents start skipping tests and hiding uncertainty.

    Lean Execution removes the waste and keeps the substance.

    What it does

    • Acts instead of narrating: no plan announcements for obvious work, no tool commentary.
    • Retrieves narrowly: search before read, line ranges instead of whole files, reuse of prior output.
    • Decides without micro-confirmations: proceeds on reversible decisions; asks one precise question only for irreversible, destructive or unknowable ones.
    • Verifies by risk: a 10-row risk matrix from typo fixes to production deploys, each with a minimum check.
    • Reports in four lines: DONE / VERIFIED / BLOCKED / NEXT, where VERIFIED names the actual check run.
    • Holds a quality boundary: never skips required tests, never invents results, never hides partial work.

    What's inside (27 files)

    • SKILL.md: core rules, activation phrases, risk matrix, ask-or-proceed rule, report format
    • references/: anti-patterns with bad vs. good examples, quality boundary, verification playbook, retrieval playbook, modes guide
    • templates/: ready-to-paste rules for Claude Code (CLAUDE.md), Cursor (.mdc and .cursorrules), Codex CLI (AGENTS.md), GitHub Copilot, plus a one-line session starter
    • evals/: 10 realistic test tasks (bug fix, refactor, failing CI, risky migration, auth change...) with pass/fail checklists, and a benchmark protocol to measure tokens and turns with vs. without the skill on your own work
    • examples/: 3 illustrative before/after transcripts

    Modes

    lean (default) · deep exhaustive analysis · status result/blocker/next only · continue resume without recap

    Install in 30 seconds

    Claude Code: drop the folder in ~/.claude/skills/. Cursor: copy templates/lean-execution.mdc to .cursor/rules/. Codex CLI: append the AGENTS.md snippet. Copilot: append the copilot-instructions snippet.

    Measured results (A/B test, Claude Code + Sonnet, 18 sessions)

    Without skillWith skill
    Tasks solved correctly9/99/9
    DONE / VERIFIED / BLOCKED / NEXT report0/97/9
    Regression test added (failing-test task)0/32/3
    Output tokens (median)baseline+19% to +50%

    Honest note: on short tasks with a concise modern model, the skill did not reduce tokens; it adds verification work. Its measured value is verification discipline and predictable reports.

    Minimum sufficient context. Minimum necessary narration. Maximum useful execution. No quality sacrifice.

    Does not reduce tokens on short tasks with concise modern models: in our A/B test (Claude Code + Sonnet) it used 19-50% more output tokens due to added verification. Long multi-step sessions and agents other than Claude Code are not yet benchmarked. It is a behavior skill: results depend on the agent following its instructions (structured report adopted in 7/9 runs).

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Requires

    vitest
    Node.js
    Git

    Permissions

    Read Files
    Write Files
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    Not on the tasks we measured. In an A/B test with Claude Code + Sonnet (3 short coding tasks, 18 sessions), the skill used 19% to 50% more output tokens, because it adds instructions and extra verification. Correctness was equal (9/9). What it adds is verification discipline and predictable reports. The package includes a benchmark protocol so you can measure it on your own work.

    Any SKILL.md-compatible agent. Ready-to-paste rules are included for Claude Code (CLAUDE.md), Cursor (.mdc and .cursorrules), Codex CLI (AGENTS.md) and GitHub Copilot, plus a one-line session starter for any other agent.

    No. A risk matrix sets a minimum verification for each task type, from re-reading the diff for a typo to dry-runs and explicit confirmation for migrations, auth, payments and deploys. The VERIFIED line must name the check actually run, and disabling tests to make CI pass is explicitly forbidden.

    27 files: SKILL.md, 5 reference playbooks (anti-patterns, quality boundary, verification, retrieval, modes), per-agent templates, 10 eval tasks with pass/fail checklists, a benchmark protocol, 3 illustrative before/after examples and a README with install steps.

    Same tasks, with vs. without the skill: tasks solved 9/9 vs 9/9; four-line DONE / VERIFIED / BLOCKED / NEXT report 7/9 vs 0/9; regression test added on the failing-test task 2/3 vs 0/3; output tokens +19% to +50%. Long multi-step sessions and other agents are not yet tested.

    New in Agents & Orchestration