IrredenEngine: Skill for Claude Code

.claude/skills/polish-checkpoint/SKILL.md

polish-checkpoint is a skill for Claude Code from jakildev/IrredenEngine. It costs 104 tokens per session (610 once invoked), scanned A, original, MIT.

A checkpoint workflow for reviewing uncommitted code changes, simplifying the changed files, and building the affected target without committing or pushing anything.

In plain words
What is it for?
Use it when you want a mid-session self-review, cleanup, and targeted build before deciding whether to commit.
Why use it?
It lets you check code quality and build status partway through a task while keeping the working tree available for more edits.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is jakildev/IrredenEngine's own configuration. It tells Claude Code how to work on IrredenEngine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything IrredenEngine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/.claude/skills/polish-checkpoint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jakildev/IrredenEngine

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for polish-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakildev/irredenengine/polish-checkpoint/github.svg)](https://agentmods.dev/skills/jakildev/irredenengine/polish-checkpoint)
Your own site
<a href="https://agentmods.dev/skills/jakildev/irredenengine/polish-checkpoint"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/polish-checkpoint/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for polish-checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakildev/irredenengine/polish-checkpoint"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/polish-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00104 $0.00610
Opus 5.5 $0.00042 $0.00244
Sonnet 5.5 $0.00021 $0.00122
Haiku 4.5 $0.00010 $0.00061

Measured 2d ago against content hash 81f3d6a841b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

polish-checkpoint 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 2d 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.

.claude/skills/polish-checkpoint/SKILL.md · 54 lines

What it actually says

polish-checkpoint

The pre-commit half of commit-and-push for the Cursor / human-in-the-loop flow. Either branch is fine — cursor flow works off master with a dirty tree until commit time — and the skill never switches branches.

If git status is clean and there are no unpushed commits, report "nothing to check" and exit.

  1. git rev-parse --abbrev-ref HEAD, git status, git diff --stat, git diff. Read the most specific CLAUDE.md for each module the diff touches.
  2. Skill: simplify. Re-check git status afterwards; if simplify left the tree clean, report that and stop.
  3. Build (code diffs only — a docs/markdown-only diff skips this):
    fleet-build --target <touched-target>
    
    A creation diff builds that creation's target; an engine module diff builds a creation that exercises it (IRShapeDebug for render/math/system, the most representative demo otherwise) plus IrredenEngineTest when engine/ changed; a header-only prefab diff builds any creation that includes it. Not the all-targets build — that is commit-and-push's job. A broken build is reported, not fixed, in this pass; bisecting the session's edits (most recent first) is usually faster than reading the compiler error.
  4. Report:
    polish-checkpoint:
      branch: <branch-name>  (<N> file(s) dirty, <M> hunk(s))
      simplify: applied <X> auto-fix(es), reported <Y> finding(s)
      build:    <target>   clean           (or: broken — see below)
      reported findings:
        - <path:line> — <finding>
    
    Clean: "Working tree is polished and the build is green. Keep iterating, or invoke commit-and-push when ready to PR."

No git operations, no branch switching, no tests, no build fixes, no following up with commit-and-push unless asked. Any unwanted simplify edit reverts with git checkout -- <path>.

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. 2d ago First seen · 54 lines · 104 tokens per session scan A 81f3d6a841b0

Subscribe to this mod's changes

polish-checkpoint is a skill published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 610 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-07.

Related

polish-checkpoint compared with skills from other repositories

polish-checkpoint next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
polish-checkpointjakildev/IrredenEngineSkill10todayMITA104Claude Code
git-advanced-workflowswshobson/agentsSkill42kyesterdayMITA54Claude Code
agent-merge-conflict-arbiterNousResearch/hermes-agentSkill262kyesterdayMITA19Claude Code, Codex
enable-check-includes-strictchromium/chromiumSkill25kyesterdayBSD-3-ClauseA70Claude Code, Codex
resolve-handoffomnigent-ai/omnigentSkill11kyesterdayApache-2.0A23Claude Code, Codex
reproduce-and-fix-issuesbacknotprop/pstackSkill3.8k2d agoMITA48Claude Code, Cursor
cy-orquestrate-issuecompozy/compozySkill2.9kyesterdayMITA94Claude Code, Codex