AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Agent Work Reviewer Maintainer

skill-undertone0809-rudder-agent-work-reviewer-maintainer · by Undertone0809

Use when reviewing Rudder agent work, Codex sessions, PRs, commits, UI, releases, regressions, proposals, or agent outcomes for product correctness, evidence quality, scope, architecture, and handoff trust.

↗ Website ↗ Repository
— No reviews yet
0 installs
5 views
0.0% view→install

Install

$ agentstack add skill-undertone0809-rudder-agent-work-reviewer-maintainer

✓ 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-undertone0809-rudder-agent-work-reviewer-maintainer)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo 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 Agent Work Reviewer Maintainer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Work Reviewer Maintainer

Overview

Review completed or in-progress Rudder agent work from product, engineering, and evidence perspectives.

When to Use

Use this skill when:

  • the user asks to review a Codex session, PR, commit, diff, release, UI, proposal, or agent outcome
  • the task needs first-principles product judgment rather than implementation
  • the user asks whether validation, screenshots, CI, or handoff evidence is trustworthy
  • a reviewer verdict is needed: accept, conditional accept, needs more evidence, or reject

Do not use this skill when:

  • black-box acceptance verification as the main task; use product-acceptance-verifier-maintainer
  • implementation or fixing the issue under review unless the user switches modes
  • generic advice with no concrete artifact

Core Pattern

target artifact -> user intent -> product context -> proven evidence -> reviewer verdict

Quick Reference

| Situation | Action | | --- | --- | | Codex session review | Read local session evidence before judging | | UI or workflow review | Run the real scenario when available | | Release/Desktop review | Check live or packaged evidence | | Skill/contract review | Separate author-claimed proof from reviewer-verified proof |

Implementation

  1. Identify the target and the user job the work was supposed to solve.
  2. Collect the diff, session transcript, screenshots, tests, CI, logs, and handoff claims.
  3. Read relevant product or engineering contracts before judging behavior.
  4. Separate author-claimed proof from reviewer-verified proof.
  5. Return findings first, then verdict, blockers, and smallest next action.

Reference files are part of this skill contract. Before executing high-risk actions or final judgments, load references/runbook.md for the detailed legacy workflow, examples, validation cases, and command-level guidance.

Use evals/ when the route needs that detail; keep the entrypoint thin.

Common Mistakes

| Mistake | Fix | | --- | --- | | Reviewing only the diff when product behavior matters | Exercise or inspect the terminal product path. | | Accepting author screenshots as reviewer proof | Mark them as author-claimed unless you verified them. | | Fixing during a review-only task | Stay read-only unless the user changes the task. | | Giving a vague PM opinion | Ground every finding in file, session, UI, test, or product-contract evidence. |

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills