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.
npx skills add EternallLight/tgc-skills --skill polishgit clone --depth 1 https://github.com/EternallLight/tgc-skillsWrote 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.
[](https://agentmods.dev/skills/eternalllight/tgc-skills/polish)<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/polish"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/polish/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.
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/polish"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01429 |
| Opus 5 | $0.00032 | $0.00714 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish
One combined quality pass over changed code. Fan out three review lenses as findings-only subagents (they read, they do not edit), merge and dedupe the results, auto-apply only the safe high-confidence findings, verify the result with the repo's own tooling, and hand back the riskier findings for the user to approve.
Proceed only when the surrounding user request explicitly asks for polishing (including
direct /tgc-skills:polish invocation) or tgc-skills:ship invokes it. Do not load this
skill from unrelated requests because polishing can edit files.
This is quality plus safe bug fixes, not a deep security audit.
Why findings-only subagents
Parallel agents that edit race each other on the same files. So the subagents only report structured findings, and a single orchestrator (you) applies edits sequentially. Fan-out read, fan-in write.
Step 1 — Resolve scope
- No argument: the current work — union of
git diff --name-only,git diff --cached --name-only, and untracked files fromgit ls-files --others --exclude-standard. If all are empty, fall back togit diff --name-only HEAD~1and say you did. - Path argument: review that file/directory.
- Skip files a review can't help: lockfiles, generated code, snapshots, binaries, vendored dirs.
If there is nothing to review, say so and stop.
Step 2 — Fan out three lenses (parallel, findings-only)
Dispatch three general-purpose subagents in a single message so they run
concurrently. Give each the file list and require it to return only a JSON array
against this schema:
[{
"file": "relative/path.ts",
"line": 42,
"lens": "correctness | simplification | over-engineering",
"confidence": "high | medium | low",
"behaviorChanging": true,
"issue": "one-line description of the problem",
"fix": "concrete, specific proposed change"
}]
The three lens prompts:
- correctness — "Review these changed files for correctness bugs only: logic
errors, off-by-one, null/undefined handling, wrong conditionals, race conditions,
incorrect error handling, broken edge cases. Do NOT report style or simplification.
Set
behaviorChanging: truefor any fix that alters runtime behavior (most bug fixes do). Return findings-only JSON — do not edit files."
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.
- 12d ago First seen · 131 lines · 64 tokens per session scan A 702903714f33
polish is a skill published in the GitHub repository EternallLight/tgc-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,429 once invoked, about $0.0003 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…