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/fix-tests-parse)<a href="https://agentmods.dev/commands/axiomantic/spellbook/fix-tests-parse"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fix-tests-parse/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/fix-tests-parse"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fix-tests-parse.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 | $0.00017 | $0.00479 |
| Opus 5 | $0.00009 | $0.00239 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
fix-tests-parse 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 5d 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.
What it actually says
Phase 0: Input Processing
Invariant Principles
- Honor dependency order — Work items with
depends_onmust be resolved in the order specified by the remediation plan. - Parse completely before acting — All findings must be parsed and work items built before any fix execution begins.
- Priority drives execution order — Process critical before important before minor.
For audit_report mode
Parse the findings YAML block (root key findings: — not the document frontmatter):
findings:
- id: "finding-1"
priority: critical # critical | important | minor
test_file: "tests/test_auth.py"
test_function: "test_login_success"
line_number: 45
pattern: 2
pattern_name: "Partial Assertions"
blind_spot: "Login could return malformed user object"
depends_on: []
remediation_plan:
phases:
- phase: 1
findings: ["finding-1"]
Use remediation_plan.phases for execution order.
Fallback parsing (if no YAML block):
- Split by
**Finding #N:**headers - Extract priority from section header
- Parse file/line from
**File:** - Extract pattern from
**Pattern:** - Extract
current_codeandsuggested_fixfrom code blocks - Extract
blind_spotfrom**Blind Spot:**
Commit strategy
Ask before beginning fix execution (optional):
- A) Per-fix — each fix in a separate commit (default)
- B) Batch by file
- C) Single commit
<FINAL_EMPHASIS> Parse all findings first. Build all work items. Then act — never before. </FINAL_EMPHASIS>
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.
- 5d ago First seen · 65 lines · 17 tokens per session scan A 9bca2eb75562
fix-tests-parse is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 479 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
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
test-integration.en
Run the integration test workflow.
test.en
Run the full project test workflow.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
test
Run the project test suite and triage any failures.