Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Negatives

    1

    Negative-first development for Claude Code: red-team features, approve invariants, then test before implementation.

    Free

    1 useSecurity scanned
    Negatives

    Negatives

    Example session with this skill installed

    /negatives Implement a FastAPI endpoint: POST /tasks/{task_id}/link-email
    Request body: {"email_id": "<id>"}

    Fetch the email from MongoDB, copy subject, sender, and receivedAt into the task as _sourceEmail, and return the updated task. Use async Motor and pytest. Documents have tenant_id, and JWT middleware puts user info on request.state.

    • Read your context and instructions
    • Compiled the negatives

    Recorded evaluation: linking an email to a task

    This is a summary of the recorded evaluation, not a verbatim agent transcript or a new execution.

    Adversarial pass and human checkpoint

    The skill run identified 27 failure modes and selected 9 invariants. The read-only red-teamer examined risks such as cross-tenant reads and writes, malformed identifiers, missing records, schema drift, database failures, MongoDB operator injection, and mass assignment through unexpected body fields. The workflow paused for human approval before writing implementation.

    Executable test fence

    The run ledger records a clean pre-implementation red check and 36 final green negative tests. Tests included pinned error contracts, assertions that rejected requests performed no write, no-leak checks on database failures, and property-based malformed-input coverage.

    MeasureWithout skillWith skill
    Hidden 15-case key16/3019/30
    Tests1136
    Both tenant-isolation checksCoveredCovered

    What the evaluation taught us

    The treatment identified MongoDB operator injection and mass assignment beyond the hidden answer key. It also identified concurrent duplicate requests and read-then-write races but silently deferred them, so both scored zero in that run.

    The current skill now exposes every deferred finding at the checkpoint and requires an explicit human decision before deferring write-path idempotency and race-condition invariants. The recorded result predates that correction; it does not prove those gaps are now solved in every run.

    Next steps in your project

    Review the invariant table and deferred list. After approval, the agent writes tests and proves they fail for the intended reasons, implements until green, runs the full suite, and logs the result. Use /negatives-retro later to inspect append-only compliance and whether a controlled sabotage is caught.

    Source and complete evaluation protocol: https://github.com/suryavbhat20/Negatives/blob/main/eval/eval-pack.md

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

    About this skill

    Build against explicit failure cases

    Negatives is a negative-first development workflow for Claude Code. Before implementation, it examines how a feature could break, leak data, or be abused, then turns approved safety and correctness properties into executable tests.

    How it works

    1. Red-team the spec: a read-only agent grounds itself in your repository and identifies 15–30 failure modes across inputs, security and tenancy, concurrency, dependencies, data integrity, scale, and LLM risks when relevant.
    2. Approve the invariants: review 5–10 priority properties and the complete deferred list. You decide what gets deferred.
    3. Prove the tests: write negative tests first and verify that they fail for the intended reason.
    4. Implement inside the fence: implement until the negative suite and full test suite pass. Tests must not be weakened, skipped, or deleted to get to green.
    5. Track results: log runs and use the included negatives-retro skill to audit test history and whether the fence detects regressions.

    Tenant isolation is mandatory for tenant-scoped features. Write-path idempotency and concurrency risks require an explicit human decision before deferral. Python guidance uses pytest and Hypothesis; other stacks map the same workflow to their own tools.

    What is included

    Main SKILL.md, the read-only red-teamer agent, negatives-retro, installation instructions, MIT license, and the evaluation protocol with recorded results. Follow INSTALL.md to place the companion agent and retro skill in the correct Claude Code directories.

    Evaluation

    One recorded A/B comparison on a FastAPI/MongoDB ticket scored 16/30 without the skill and 19/30 with it against a hidden 15-item key, with 11 versus 36 tests. The treatment also identified MongoDB operator injection and mass assignment outside that key. It exposed silent deferral of race conditions, leading to an explicit deferral checkpoint. This is a single comparison, not a general reliability guarantee.

    Usage

    Run /negatives followed by a feature description. Review and approve the invariant checkpoint before tests or implementation begin. Run /negatives-retro later to evaluate the test fence. Intended for new features, endpoints, jobs, and modules; bug fixes and refactors are outside the main skill's scope.

    Source: https://github.com/suryavbhat20/Negatives

    Designed and evaluated for Claude Code; other agents have not been verified. Requires a runnable project test environment and human approval of invariants. The reported 16/30 versus 19/30 scores come from one comparison and do not establish a general reliability improvement. Current safeguards for deferred concurrency risks have not been re-evaluated in that recorded comparison. Append-only tests are enforced by instructions and audits, not an immutable technical control. Companion agent and retro skill require installation in their documented directories. Coverage depends on the approved invariants and test quality.

    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 26 days ago

    • Free with an Agensi account

    Requires

    Claude Code
    Git
    pytest (Python projects)
    Hypothesis (Python property-based tests)
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Reads feature specs, source, tests, and Git history; writes negative tests, implementation, and test configuration; executes test commands. Appends run and retro records to ~/.claude/negatives-runs.jsonl. The red-teamer agent is read-only. Retro may temporarily change one implementation line for a sabotage probe and must restore it immediately. Network and service access depend on your project, not the skill itself.

    Listed26 days ago

    What's inside

    Frequently Asked Questions

    Extract the ZIP and follow INSTALL.md. Place the main SKILL.md in ~/.claude/skills/negatives/, the red-teamer in ~/.claude/agents/, and the retro skill in ~/.claude/skills/negatives-retro/. Start a new Claude Code session and run /negatives followed by a feature description.

    It identifies failure modes and presents prioritized invariants plus every deferred finding. You approve or edit that checkpoint before tests or implementation begin.

    The workflow includes guidance for mapping pytest and Hypothesis mechanics to other test stacks. The documented evaluation used Python with FastAPI and MongoDB in Claude Code. Other agents have not been verified.

    It reviews run logs, invariant registries, and Git history for weakened tests, collects evidence of caught and escaped bugs, and can temporarily sabotage an implementation check to verify that tests detect it. The probe must be reverted and green restored.

    New in Testing & Debugging