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 developgit 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/develop)<a href="https://agentmods.dev/skills/axiomantic/spellbook/develop"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/develop/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/develop"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/develop.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 | $0.00225 | $0.02221 |
| Opus 5.5 | $0.00090 | $0.00888 |
| Sonnet 5.5 | $0.00045 | $0.00444 |
| Haiku 4.5 | $0.00022 | $0.00222 |
Grade A, and why
develop 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<BEHAVIORAL_MODE>
ENTRY GATE: ask which path, then load that path. Never read source files, write code, or run tests from this file. Everything the orchestrator needs after the choice lives in $SPELLBOOK_DIR/commands/develop-configure.md.
</BEHAVIORAL_MODE>
Invariant Principles
- Ask before spending. The ceremony cost is disclosed and chosen BEFORE any phase runs, never assumed from the phrasing that triggered this skill.
- The choice is the operator's. develop may recommend; the operator's answer is the source of truth.
- Chosen ceremony LOCKS. From the moment a ceremony path is chosen, escalation stays legal and de-escalation never becomes legal. The two honest answers to "this is taking too long" are FINISH or ABORT-and-re-invoke.
- No path is zero review except the one that exits. Both ceremony paths carry a review floor. Only "skip develop entirely" leaves the operator unguarded, and it says so out loud.
- develop stays resident on both ceremony paths. There is no auto-exit; the skill remains active to enforce the floor it sold.
Reasoning Schema
Before asking: state what the request appears to touch, and which path you would recommend and why. After the answer: confirm the chosen path is recorded, the ceremony is locked, and the correct body was loaded.
The Gate
Offer exactly these THREE options (the harness adds its own "Other"). Present each option's cost honestly; the descriptions below are the point of this gate, not decoration.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 119 lines · 225 tokens per session scan A 4a958605205e
develop is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 225 tokens to every session and 2,221 once invoked, about $0.0009 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.