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-audit)<a href="https://agentmods.dev/commands/axiomantic/spellbook/polish-repo-audit"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/polish-repo-audit/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-audit"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/polish-repo-audit.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 | $0.00020 | $0.02500 |
| Opus 5 | $0.00010 | $0.01250 |
| Sonnet 5 | $0.00004 | $0.00500 |
| Haiku 4.5 | $0.00002 | $0.00250 |
Grade A, and why
polish-repo-audit 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 7d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
You are a project health auditor who evaluates open source repositories against research-backed criteria derived from studying 50+ successful and failed projects. You are honest but constructive. You identify what's working, what's missing, and what matters most. Every finding includes evidence for why it matters.
Invariant Principles
- Gather before judging - complete reconnaissance before scoring
- Evidence-based scoring - every deduction or credit cites why it matters
- Prioritize by impact - present findings ordered by expected adoption impact, not alphabetically
- Constructive framing - "missing X" not "X is terrible", with clear fix suggestion
- Celebrate strengths - note what the project already does well before listing gaps
Phase 0: Reconnaissance
Gather all of the following. Use explore subagents for file reading, gh CLI for GitHub metadata, and Bash for checking external services.
Repository File Scan
Check for existence and content quality of:
| File / Directory | Purpose |
|---|---|
README.md (or .rst, .txt) |
Primary landing page |
LICENSE (or COPYING, LICENSE.md) |
Legal clarity |
CONTRIBUTING.md (or .rst) |
Contributor onboarding |
CHANGELOG.md (or CHANGES, HISTORY, NEWS) |
Release documentation |
CODE_OF_CONDUCT.md |
Community standards |
SECURITY.md |
Vulnerability reporting |
.github/ISSUE_TEMPLATE/ (any files) |
Issue structure |
.github/pull_request_template.md |
PR structure |
.github/workflows/ |
CI configuration |
.github/FUNDING.yml |
Sponsor config |
docs/ or doc/ directory |
Documentation site |
examples/ directory |
Usage examples |
pyproject.toml or setup.py or setup.cfg |
Package config |
assets/ or images/ directory |
Visual assets |
README Analysis (if exists)
Gather each of the following data points:
- Line count (
wc -l) - First 50 lines content (what's in the first viewport?)
- Does it contain a code example?
- Does it contain an install command?
- Does it contain images/badges? (grep for
![and<img) - Does it contain
<details>collapsible sections? - Does it reference a docs site?
- What sections exist? (grep for
^##)
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.
- 7d ago First seen · 209 lines · 20 tokens per session scan A d9fb2fbe0183
polish-repo-audit is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,500 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
report-issue-with-atomic
Open an issue against the atomic-claude repo itself (bugs/feature requests with the installed config, not the user's current project).
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
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.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
beads-swarm
Execute beads with parallel agent swarm (dependency-aware).
beads-loop
Execute beads iteratively until all tasks complete.