Clippy
- 1 repo stars
- Updated June 26, 2026
- Gunther-Schulz/coding-clippy
Drive a structured investigate-design / implement / verify coding workflow where every claim is grounded in evidence.
About
Clippy enforces a structured investigate-design, implement, then verify workflow for Claude Code, requiring every claim to be backed by evidence. A developer uses it to keep agent-driven coding rigorous and grounded instead of producing unverified output.
- Investigate-design-implement-verify
- Evidence-grounded
- Reduces hallucinated claims
- Structured workflow
Clippy by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add Gunther-Schulz/coding-clippy/plugin install clippy@coding-clippyAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Last updated | June 26, 2026 |
| Repository | Gunther-Schulz/coding-clippy ↗ |
What it does
Drive a structured investigate-design / implement / verify coding workflow where every claim is grounded in evidence.
README.md
Clippy Plugin
Build on understanding, not output.
Clippy is the Anneal framework bound to building software. It runs each task as a loop — investigate, design, re-investigate with fresh investigation, until the design no longer changes — then implements and verifies. The locked design is what advances, not whatever the AI produced first.
See ../README.md for the user pitch, install, and
modes; this file is the component map for contributors.
Installation
claude plugin marketplace add Gunther-Schulz/coding-clippy
claude plugin install clippy@coding-clippy
Trigger
- Describe a development task — the
clippyskill auto-activates Skill(skill="clippy:clippy")— explicit entry, interactiveSkill(skill="clippy:clippy", args="--auto-battle <task>")— auto-battle mode
Components
| Name | Type | File |
|---|---|---|
clippy |
Skill | skills/clippy/SKILL.md |
Inside the clippy skill
| File | Purpose |
|---|---|
SKILL.md |
The orchestrator — conducts the run, holds transitions and loopbacks |
phases/investigate-design.md |
The investigation-and-design phase: the cycle loop to [READY] |
phases/implement.md |
Carries out the locked design |
phases/verify.md |
Checks the work against the design and the lenses |
references/foundations.md |
The basis rule, evidence-bearing artifacts, inspection |
references/tracker.md |
The two-track status machine and tracker persistence |
references/lenses.md |
The standardized coding lens set |
references/post-run-review.md |
Optional post-[PASSED] review procedure — operator-invoked, in-session output, no persistence |
License
MIT
Related skills
Improve Codebase ArchitectureSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.566k196k
Caveman ReviewGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.270k94.7kCodebase DesignShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.266k196kCavecrewDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.220k94.7kCode ReviewReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.201k196k
Requesting Code ReviewDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.183k264k