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 optimizing-instructionsgit 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/optimizing-instructions)<a href="https://agentmods.dev/skills/axiomantic/spellbook/optimizing-instructions"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/optimizing-instructions/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/optimizing-instructions"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/optimizing-instructions.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 | $0.00073 | $0.01600 |
| Opus 5.5 | $0.00029 | $0.00640 |
| Sonnet 5.5 | $0.00015 | $0.00320 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
optimizing-instructions 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction Optimizer
Invariant Principles
- Smarter AND smaller - Compression is only valid when capability is fully preserved
- Evidence over claims - Show token counts before/after; verify no capability loss
- Unique value preservation - Deduplicate redundancy, keep distinct behaviors
- Clarity at critical points - Brevity yields to clarity for safety/compliance sections
Reasoning Schema
Rule-section guard. If the input contains a canonical ## Rules
section (managed by /crystallize), optimizing-instructions MUST
refuse to operate on the file and emit the following error:
Input contains a canonical Rules section (managed by /crystallize). Use /crystallize for rule-aware compression.
The canonical Rules section is the FIRST ## Rules heading after the <ROLE> block (or the first ## Rules heading if no <ROLE> block exists). Any later ## Rules heading is treated as ordinary content, not the canonical section.
Rationale: silently compressing a file with a canonical Rules section
would defeat /crystallize's rule-preservation contract by mutating
rule text from a sibling tool. The guard makes the contract holistic
across the prompt-compression toolset.
Inputs
| Input | Required | Description |
|---|---|---|
instruction_file |
Yes | Path to skill, prompt, or CLAUDE.md to optimize |
target_reduction |
No | Desired token reduction % (default: maximize) |
preserve_sections |
No | Sections to skip optimization (safety, legal) |
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 · 191 lines · 73 tokens per session scan A fba99ee6f2b8
optimizing-instructions is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,600 once invoked, about $0.0003 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.