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 using-skillsgit 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/using-skills)<a href="https://agentmods.dev/skills/axiomantic/spellbook/using-skills"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/using-skills/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/using-skills"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/using-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.01073 |
| Opus 5.5 | $0.00022 | $0.00429 |
| Sonnet 5.5 | $0.00011 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
using-skills 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invariant Principles
- Skill invocation precedes all action. Check skills BEFORE responding, exploring, clarifying, or gathering context.
- A 1% probability of applying triggers invocation. The bar is deliberately at the floor: if a skill plausibly applies, load it. A skill loaded needlessly costs tokens; a skill missed costs quality on work already underway, which is the far more expensive error. Low-signal turns are excluded by Principle 3, not by raising this bar.
- Ignore low-signal turns. Never invoke a skill for simple status checks, "where are we" questions, or short clarifications.
- Skills encode institutional knowledge. They evolve. Never rely on memory of skill content.
- Process determines approach; implementation guides execution.
Inputs
| Input | Required | Description |
|---|---|---|
user_message |
Yes | The user's current request or question |
available_skills |
Yes | List of skills from Skill tool or platform |
conversation_context |
No | Prior messages establishing intent |
Outputs
| Output | Type | Description |
|---|---|---|
skill_invocation |
Action | Skill tool call with appropriate skill name |
todo_list |
Action | TodoWrite with skill checklist items (if applicable) |
greeting |
Inline | Session greeting after init |
Session Init
On first message, greet: "Welcome to spellbook-enhanced Claude."
Decision Flow
Message received
↓
<analysis>
Could ANY skill apply? (1% threshold)
</analysis>
↓ yes
Invoke Skill tool → Announce "Using [skill] for [purpose]"
↓ no skill matches
Proceed normally
↓
<reflection>
Does skill have checklist?
</reflection>
↓ yes → TodoWrite per item
↓
Follow skill exactly → Respond
Correct: "fix the login bug" → <analysis> finds debugging skill → invoke debugging skill BEFORE reading any files.
Incorrect: "fix the login bug" → read login.py "to understand" → rationalization. Skill check comes first.
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 · 123 lines · 56 tokens per session scan A 1900a2dd8139
using-skills is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,073 once invoked, about $0.0002 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.