AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Quality

skill-poteto-noodle-quality · by poteto

Post-cook quality gate. Reviews completed cook work for correctness, scope discipline, and principle compliance. Emits stage_message events with findings. Triggers after execute stages, on '/quality', 'review this', 'check the work', 'assess quality'.

No reviews yet
0 installs
33 views
0.0% view→install

Install

$ agentstack add skill-poteto-noodle-quality

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-poteto-noodle-quality)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
6mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Quality? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Quality

Review completed cook work. Emit a stage_message event with your assessment. See references/stage-message-schema.md for the event schema.

Operate fully autonomously. Never ask the user.

Step 0 -- Load Principles

Read brain/principles.md and follow every [[wikilink]]. These govern the review. Do NOT skip this.

Assessment Pipeline

Run in order. Stop early and reject on any high-severity finding.

1. Scope Check

  • Read the plan phase the cook was assigned (from the cook's initial prompt or mise context).
  • Run git diff --stat and git log --oneline for the cook's commits.
  • Flag files changed outside the plan phase's stated scope as scope violations.

2. Code Quality

  • go vet ./... and go test ./... must pass.
  • Run sh scripts/lint-arch.sh if it exists.
  • Check error handling follows project conventions (failure-state messages, not expectation messages).

3. Principle Compliance

  • For each changed file, check against loaded principles.
  • Common violations: bolted-on changes instead of redesign (redesign-from-first-principles), missing verification (prove-it-works), unnecessarily added complexity (subtract-before-you-add).

4. Test Evidence

  • New behavior must have new tests.
  • Tests must assert outcomes, not implementation details.
  • Check coverage of edge cases mentioned in the plan phase.

5. Runtime Verification

  • If the plan phase specifies runtime checks, verify they were performed.
  • "It compiles" is not verification.

Verdict

Emit a stage_message event with your assessment:

noodle event emit --session $NOODLE_SESSION_ID stage_message --payload ''

Accept: Emit with blocking: false. The pipeline continues and the scheduler sees the green light.

{ "message": "All checks pass. Tests green, scope clean.", "blocking": false }

Reject: Emit with blocking: true (or omit blocking). The scheduler reads findings and decides (retry, add oops stage, or abort).

{ "message": "Rejected: 3 high issues. [1] Missing test for edge case in handleCompletion. [2] Scope violation: modified cook_merge.go outside plan phase scope. [3] Error message uses expectation form.", "blocking": true }

Write the message as natural language the scheduler can act on. Include specific file paths, line context, and principle violations so the scheduler can brief the retry cook.

Non-blocking Issues

Issues that don't warrant rejection (style nits, minor improvements, documentation gaps): file as backlog items via the backlog adapter.

Principles

  • [[prove-it-works]]
  • [[outcome-oriented-execution]]

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.