Review Outcomes — Development agent for Claude Code
Periodic post-ship outcome review — grade shipped merges against the fixes and reverts that followed, and against the gate verdicts recorded at the time.
How to install Review Outcomes
Installs to ~/.claude/agents/jacquardlabs-studious-review-outcomes.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jacquardlabs/studious/HEAD/agents/review-outcomes.md -o ~/.claude/agents/jacquardlabs-studious-review-outcomes.md Restart Claude Code, or start a new session, for it to be picked up.
What Review Outcomes does
name: review-outcomes description: Periodic post-ship outcome review — grade shipped merges against the fixes and reverts that followed, and against the gate verdicts recorded at the time. Not diff-scoped; reads git history over a lookback window. tools: Read, Glob, Grep, Bash, Write model: sonnet effort: medium
Outcome review
A periodic review of what happened *after* the merge. Every other review in this plugin judges work before it ships; this one reads default-branch history, fin
Alternatives in Development
- Docs Drift Review — Given a session's commits or diff, finds the docs that the change made wrong — stale paths and symbols, checkl 7.2k ★
- Ac Claim Verifier — Phase 3.4 claim verifier 115 ★
- Product Owner Proxy — Define business intent as user stories with clear acceptance criteria and measurable outcomes 108 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Review Conformance
Read-only reviewer that checks an implementer's worktree against the brief - goal met, out-of-scope respected,
Outcome Predictor
Independent reviewer for reform analyses. Mode 1 (predict) reads ONLY the reform provisions and predicts expec
App Backend Module Agent
Build ONE backend feature module (routes/handlers + services + validation + tests) of an application from a se
Shipper
Release engineer that handles the last mile from working code to shipped product — tests, changelog, version b
Value Critic
Upstream VALUE gate. Judges ONE candidate idea BEFORE any code is written — does it plausibly move the product
Winterbotham
Consolidates review findings into canonical reports. Two modes - cross-discipline (merges Fagan + Oppenheimer
Related Skills
Registry Scanner
Periodic, GitHub-Actions-as-SaaS security scanner for agent skills declared in the Coder registry catalogue. R
Outcome Pro
Assess business, product, marketing, engineering, and operational outcomes against intent using authorized agg
Verify Done
5pm ritual. Check today's outcomes, log what shipped, flag what slipped, write tomorrow's 3.