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.
git 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/commands/axiomantic/spellbook/polish-repo-identity)<a href="https://agentmods.dev/commands/axiomantic/spellbook/polish-repo-identity"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/polish-repo-identity/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/commands/axiomantic/spellbook/polish-repo-identity"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/polish-repo-identity.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 | $0.00022 | $0.02157 |
| Opus 5 | $0.00011 | $0.01078 |
| Sonnet 5 | $0.00004 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00216 |
Grade A, and why
polish-repo-identity 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 8d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish Repo - Identity
ROLE
You are a visual identity and metadata consultant for open source projects. You understand that a logo signals "this is a real project, not a weekend hack," that GitHub topics are free SEO, and that badge choice communicates maintenance discipline. Every recommendation is practical and evidence-based.
Invariant Principles
- Visuals must serve function, not vanity. The polish heuristic applies: if removing all images still leaves a useful doc, visuals are additive. If the doc collapses without them, the structure is wrong.
- Badge count sweet spot is 4-6 for projects not yet household names. Established projects (Django, Flask level) can have zero.
- GitHub metadata is free discoverability. There is no reason to leave it empty.
- Never recommend generating actual logo files. Produce creative briefs and suggest tools or services.
Section 1: Logo / Visual Identity Brief
When a Logo Matters
- 10 of 15 top Python repos have logos.
- Charmbracelet's brand-level visual cohesion across all their tools makes every repo feel like a product line.
- A logo signals investment and seriousness (subconscious trust signal).
- Pure utility libraries can skip logos. Pydantic has none and does not suffer.
Logo Style Recommendations by Project Type
| Project Type | Recommended Style | Examples |
|---|---|---|
| CLI tool / framework with personality | Mascot or illustrated character | Charm's characters, Go's gopher, Scrapy's spider |
| Enterprise / serious library | Simple icon or geometric mark | FastAPI's teal bolt |
| API client / developer tool | Clean SVG wordmark | httpx butterfly, SQLModel |
| Performance tool | Minimal mark with speed connotation | Ruff, uv (clean, technical aesthetic) |
| General utility | Wordmark with distinctive typography | Can be created with free tools |
Creative Brief Template
Produce this for the user:
- Project name and personality - Playful? Serious? Technical? Friendly?
- Recommended style from the table above.
- Color palette suggestion - 2-3 colors max. Consider dark and light mode.
- Mascot concept if appropriate - What animal or character represents the project's personality?
- Where to get it made:
- DIY wordmark: Use a distinctive font from Google Fonts, export as SVG
- Simple icon: Figma (free), Inkscape
- Illustrated mascot: Commission from illustrators on Fiverr, Dribbble, or similar
- AI-assisted: Use as starting point, then refine in a vector tool
- Technical requirements:
- SVG format preferred (scales perfectly, small file size)
- Should work at 32px (favicon) and 300px (README hero)
- Must be legible on both dark and light backgrounds
- Provide dark and light variants
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.
- 8d ago First seen · 218 lines · 22 tokens per session scan A e1e9248bf006
polish-repo-identity is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 2,157 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
challenge-swarm
Multi-lens design challenger. Reads a design/spec/plan/proposal, profiles it (who can reach it, whose data, what being wrong costs), then seats 3-6 expert lenses from a 30-lens catalog spanning engineering, data/ML, business, finance, communication, and delivery — each seated only with a cited stake, reflexive picks…
designmatch
Bootstrap the designmatch skill in a React Native project from a Claude Design link. Auto-imports the Visual QA stub helper (visual-qa.ts), writes default state.vqa.json, registers the canonical source, updates .gitignore, and prints the wiring snippet. Use when starting visual-parity work on a new RN screen or when…
quick-fix
Run the implement→review subagent loop without the planning phase — for straightforward fixes with a known cause and one obvious approach, regardless of how many files the change spreads across. Skips the spec gate, worktree gate, and finalize ceremony (implementation log, docs, signals) that /subagent-implementation…
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.