polish

A local review-and-fix loop that repeatedly checks changes on a feature branch, applies findings that can be resolved automatically or by the agent, and records issues needing human judgment.

In plain words
What is it for?
Use it to review a branch, apply permitted fixes, rerun the review, and produce an audit record with remaining sign-off items.
Why use it?
It helps reduce repeat review cycles by addressing resolvable problems before handoff while keeping decisions that require a person clearly marked.

Skill for Claude CodeCodex

Part of the planwright plugin — 11 skills, 9 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/inkatze/planwright/polish
Any agent
npx skills add inkatze/planwright --skill polish
Clone the repo
git clone --depth 1 https://github.com/inkatze/planwright

Made for: Claude Code, Codex.

Or install planwright, the plugin that ships this one along with the rest of its 11 skills, 9 hooks.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00094 $0.03084
Opus 5 $0.00047 $0.01542
Sonnet 5 $0.00019 $0.00617
Haiku 4.5 $0.00009 $0.00308

Measured 3d ago against content hash 2721de80f394, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/polish/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/polish

The autonomous act-then-review loop (REQ-E2.1, D-12): repeat the /self-review pass against the feature branch until it drains every action disposition and only irreducible Needs-human-judgment forks (if any) remain, then hand off the audit record. Polish is local-only: it never pushes and never creates or touches a PR; its only remote interaction is the read-only fetch that pins the base at pre-flight, and iterations never touch the remote (nested /self-review passes reuse the pinned base without fetching). The pending-sign-off checklist it emits reaches the draft PR through whichever skill owns PR creation (/execute-task per REQ-E1.5, or a standalone /self-review).

Doctrine

Resolve and read the same rule docs as /self-review via the rule-doc resolution convention (scripts/resolve-rule-doc.sh <doc-name> or the documented PLANWRIGHT_ROOT/CLAUDE_PLUGIN_ROOT chain): discovery-rigor, validation-rigor, finding-categorization, gate-wiring, research-rigor, refactor-instinct, security-posture, proportionality. All load at run start except research-rigor, read point-of-use inside the nested /self-review pass's finding-validation (the iteration loop below). Their definitions govern wherever this skill names a concept. If a rule doc does not resolve, halt with a clear message naming the missing doc and the chain consulted.

Doctrine manifest (the reading model above in machine-parseable form, per doctrine/instruction-hygiene.md; run-start docs load before work begins, point-of-use at the named step):

Doctrine: run-start discovery-rigor Doctrine: run-start validation-rigor Doctrine: run-start finding-categorization Doctrine: run-start gate-wiring Doctrine: point-of-use research-rigor (the nested /self-review pass's finding-validation) Doctrine: run-start refactor-instinct Doctrine: run-start security-posture Doctrine: run-start proportionality

Invocation modes

Read the literal flag --nested from $ARGUMENTS at the start of the run:

Read the full file on GitHub · 240 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 240 lines · 94 tokens per session scan A 2721de80f394

Subscribe to this mod's changes

polish is a skill published in the GitHub repository inkatze/planwright (3 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 3,084 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

seeds-issue-audit

Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".

jayminwest/warren · 67 tokens

good-first-issue-batch

File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…

jayminwest/warren · 80 tokens

os-eco-dep-sync

Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.

jayminwest/warren · 69 tokens

release

Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.

jayminwest/warren · 39 tokens

create-coordclaw-team

A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.

CoordClaw/CoordClaw · 42 tokens

write-file

Replaces OpenClaw built-in write tool for all plain text writing, providing.

CoordClaw/CoordClaw · 618 tokens