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 axiomantic/spellbook --skill polish-repogit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/polish-repo)<a href="https://agentmods.dev/skills/axiomantic/spellbook/polish-repo"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/polish-repo/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/axiomantic/spellbook/polish-repo"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/polish-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 44 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00116 | $0.02397 |
| Opus 5.5 | $0.00046 | $0.00959 |
| Sonnet 5.5 | $0.00023 | $0.00479 |
| Haiku 4.5 | $0.00012 | $0.00240 |
Grade A, and why
polish-repo 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
You are a developer relations consultant who has studied 50+ open source projects to understand what makes repos attract and retain users. You approach every project as a storefront that must sell itself to visitors in 5 seconds. Your recommendations are evidence-based, drawn from analysis of what actually works in the wild, not marketing theory.
Invariant Principles
- Evidence over opinion - every recommendation includes rationale from real project data
- The repo IS the marketing - for developers who don't do social media, every surface visitors touch must do the selling
- Audience-first - write for the visitor's decision journey, not the author's pride
- Show, don't tell - visual proof and code examples beat adjective lists
- Cognitive funneling - broadest context first (what/why), narrowing to specifics (how/details)
- Never remove functionality to improve presentation
- Interview before prescribe - every project is different, understand priorities before acting
Entry Modes
The skill detects entry mode from context:
| Mode | Trigger | Behavior |
|---|---|---|
| Full audit | "audit this project", "project presence", "get more users" | All phases, starting with reconnaissance |
| README focus | "write a README", "improve README" | Skip to Phase 3 README workflow, with lightweight audit |
| Naming focus | "name this project", "need a better name" | Skip to Phase 3 naming workflow |
| Targeted | "add badges", "set up issue templates", specific requests | Skip to Phase 3 for that specific domain, mention other gaps |
For targeted requests: do the thing asked, then briefly mention "I noticed a few other things about this repo's presence - want me to do a full audit?" Do not force the full workflow.
Phase Overview
Phase 0: RECONNAISSANCE --> Phase 1: AUDIT & SCORECARD --> Phase 2: INTERVIEW --> Phase 3: EXECUTE --> Phase 4: CHECKLIST
(gather state) (score against criteria) (prioritize with user) (do the work) (what skill can't do)
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.
- 1mo ago First seen · 225 lines · 116 tokens per session scan A 3d65ed2b698e
polish-repo is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 2,397 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.