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 agentmods add commands/axiomantic/spellbook/verifygit 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/verify)<a href="https://agentmods.dev/commands/axiomantic/spellbook/verify"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/verify.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00846 |
| Opus 5 | $0.00015 | $0.00423 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
verify 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
Invariant Principles
- Evidence Precedes Claims: No completion statement without fresh command output in same message
- Spirit Over Letter: Paraphrases, implications, synonyms all count as claims
- Verification Is Binary: Partial checks prove nothing; full command or no claim
- Independence Required: Agent/tool reports require independent verification
- Exhaustion Irrelevant: Fatigue, confidence, "just this once" are not evidence
Gate Function Protocol
Evidence Requirements
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Output: 0 failures | Previous run, "should pass" |
| Linter clean | Output: 0 errors | Partial check |
| Build succeeds | Exit 0 | Linter passing |
| Bug fixed | Original symptom resolved | Code changed |
| Regression test | Red-green cycle verified | Passes once |
| Agent completed | VCS diff shows changes | Agent reports success |
| Requirements met | Line-by-line checklist | Tests passing |
Red Flags: STOP
- "should", "probably", "seems to"
- Satisfaction before verification ("Great!", "Done!")
- About to commit/push/PR without fresh evidence
- Trusting agent success reports
- ANY wording implying success without running verification
Rationalization Prevention
| Excuse | Reality |
|---|---|
| "Should work now" | RUN verification |
| "I'm confident" | Confidence != evidence |
| "Agent said success" | Verify independently |
| "Partial check enough" | Partial proves nothing |
| "Different wording" | Spirit over letter |
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.
- 3d ago First seen · 113 lines · 31 tokens per session scan A becaf09d3fca
verify is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 846 once invoked, about $0.0002 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
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
autocommit
Toggle auto git commits on/off for this project. Run without args to see status, or with "on"/"off" to set.
commit-push-pr
머지 전 /sync-docs 문서 동기화 의무 게이트 → 검증 → 커밋 & PR & 머지 + MCP 알림 (v7).
quick-commit
간단한 수정용 빠른 커밋 (v6).