Stats
Actions
Tags
From ctoc
**First action:** read the full plan ancestry before doing anything else.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
ctoc:agents/-shared/ancestry-readThe summary Claude sees when deciding whether to delegate to this agent
**First action:** read the full plan ancestry before doing anything else. The chain (read in order): 1. **Vision** (`plans/vision/<slug>.md` or `plans/done/<slug>.md` after decomposition) — the WHY 2. **Canvas** (`plans/canvas/<slug>.md`, if exists — optional layer) — the business model context 3. **Functional** (`plans/functional/<slug>.md`) — the WHAT + WHO 4. **Implementation** (`plans/imple...
First action: read the full plan ancestry before doing anything else.
The chain (read in order):
plans/vision/<slug>.md or plans/done/<slug>.md after decomposition) — the WHYplans/canvas/<slug>.md, if exists — optional layer) — the business model contextplans/functional/<slug>.md) — the WHAT + WHOplans/implementation/... or plans/todo/... for the current plan) — the HOWFor step-N agents where N ≥ 5 (Planner / Designer / Spec / Test / Implementer / Reviewers): this is mandatory. Skip it and you'll drift on Opus 4.7's literal interpretation.
Use exact step labels: TEST, PREPARE, IMPLEMENT, REVIEW, OPTIMIZE, SECURE, VERIFY, DOCUMENT, FINAL-REVIEW. The plan-validator (src/lib/plan-validator.js) rejects plans with non-matching labels — non-matching labels are not a stylistic preference, they're a hard block.
Declared frontmatter is authoritative. When the plan says effort: xhigh, use xhigh thinking. When it says files: [...], those are the files you may touch (the enforcement hook will block edits outside that list).
npx claudepluginhub robotijn/ctoc --plugin ctocExpert in strict POSIX sh scripting for portable Unix-like systems. Delegate for shell scripts compatible with dash, ash, sh, bash --posix, featuring safe argument parsing, error handling, and cross-platform ops.
Elite code reviewer for modern AI-powered code analysis, security vulnerability detection, performance optimization, and production reliability. Masters static analysis tools and security scanning.
Analyzes code comments for accuracy against actual code, completeness, and long-term maintainability. Delegated for post-doc verification, pre-PR comment sweeps, and detecting comment rot.