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 instruction-engineeringgit 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/instruction-engineering)<a href="https://agentmods.dev/skills/axiomantic/spellbook/instruction-engineering"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/instruction-engineering/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/instruction-engineering"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/instruction-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00085 | $0.01808 |
| Opus 5.5 | $0.00034 | $0.00723 |
| Sonnet 5.5 | $0.00017 | $0.00362 |
| Haiku 4.5 | $0.00009 | $0.00181 |
Grade A, and why
instruction-engineering 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction Engineering
Invariant Principles
-
Simplicity First: Shortest prompt that achieves the goal. Add complexity only when simplicity fails. Every line must justify its existence.
-
Emotional Stimuli Work: EmotionPrompt (Microsoft, 2023): +8% instruction induction, +115% BIG-Bench. EP02 = "This is very important to my career." EP06 = "You'd better be sure." NegativePrompt (IJCAI 2024): +12.89% instruction induction. NP = consequences for failure framing.
-
Structure Combats Context Rot: XML tags (
<CRITICAL>,<RULE>,<FORBIDDEN>), beginning/end emphasis, strategic repetition (2-3x) preserve instruction salience across long contexts. -
Personas Need Stakes: Bare personas ("act as expert") show mixed results. Persona + emotional stimulus (EP02/EP06/NP) shows highest effectiveness.
-
Skills Invoke, Not Duplicate: Reference skills via
Skilltool. Provide CONTEXT only. Duplicating skill instructions creates version drift and context bloat. -
Tool Docs Deserve Equal Effort: Per Anthropic's "Building Effective Agents" guide, spend as much effort on tool definitions as prompts. See
/ie-tool-docs.
Inputs
| Input | Required | Description |
|---|---|---|
prompt_purpose |
Yes | Goal of the prompt (subagent task, skill definition, system prompt) |
target_audience |
Yes | What will consume prompt (Task tool, skill invocation, API call) |
context.task_description |
Yes | What the prompt should accomplish |
context.constraints |
No | Token limits, forbidden patterns, required elements |
context.existing_prompt |
No | Current prompt to improve (for revision tasks) |
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 · 170 lines · 85 tokens per session scan A de8c8cf33c68
instruction-engineering is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 1,808 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.