Self Containment Reviewer — Development agent for Claude Code
Read-only reviewer that verifies every committed-facing artifact in the diff is self-contained — fully understandable by a brand-new engineer with zero access to the author's local notes and zero memo.
How to install Self Containment Reviewer
Installs to ~/.claude/agents/parker-plextrac-pt-doots-self-containment-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/parker-plextrac/pt-doots/HEAD/agents/self-containment-reviewer.md -o ~/.claude/agents/parker-plextrac-pt-doots-self-containment-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Self Containment Reviewer does
name: self-containment-reviewer description: Read-only reviewer that verifies every committed-facing artifact in the diff is self-contained — fully understandable by a brand-new engineer with zero access to the author's local notes and zero memory of this ticket's private history. Flags leaked notes/ paths, internal plan-label shorthand (C1/C2/C3, D1/D2, "Option A"), private process/history references, reviewer/person names, and dangling context. Spawned at Step 4c (quality gate) in parallel
Alternatives in Development
- Token Change — Safely perform a self-contained Graphite token/color change end-to-end (edit primitive → regenerate → gate) in 452 ★
- Cold Verifier — Phase 11 cold verification agent that independently re-verifies CRITICAL and HIGH findings with zero prior con 125 ★
- Book Orchestrator — Fully autonomous book genesis pipeline 114 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Repo Skill Author
Authors a new SHARED skill that ships with the PAL repo (committed to assets/skills/). Invoked by the author-p
Weavie Behavior Auditor
Scans a range of committed diffs for egregious behavioral pathologies — approaches that are cost-pathological,
ADR Generator
Use this agent to author a new Architecture Decision Record (ADR). Hand it the decision, the alternatives, and
Review Judge
Neutral zero-context judge for the adversarial-review skill. Rules ONLY on findings the author disputed — read
Maya Angelou Writer
Use this agent for copywriting, brand storytelling, customer-facing messaging, email sequences, and any writin
Release Failure Analyzer
MUST BE USED when release.yml fails (Phase 3 of releasing-erfana skill, on non-zero gh run watch --exit-status
Related Skills
Vibe To Ship
Productionized graph engineering for everyday vibe coders — a drop-in agent skill (Claude Code + opencode) tha
AI Native Sdlc Skills
Unofficial Claude Code skills adapted from Anthropic's The AI-Native SDLC playbook — the committed-artifact ch
Claude Interaction Tests
Test whether your CLAUDE.md actually works. A Claude Code skill that restructures agent-facing docs (CLAUDE.md