ie-techniques

ie-techniques is a command for Claude Code from axiomantic/spellbook. It costs 20 tokens per session (2,076 once invoked), scanned A, original, MIT.

A reference command describing 16 techniques for writing instructions for AI models, including emotional prompts, negative prompts, research sources, and measurable effects.

In plain words
What is it for?
Use it as a reference when designing or reviewing prompts that need specific instruction-writing techniques.
Why use it?
It helps prompt authors choose documented techniques and connect them to observable improvements in agent output.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents.

Good fit Use it as a reference when designing or reviewing prompts that need specific instruction-writing techniques.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/ie-techniques
Install

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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

Wrote 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.

agentmods badge for ie-techniques

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/ie-techniques/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/ie-techniques)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/ie-techniques"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/ie-techniques/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.

agentmods 80×15 button for ie-techniques

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/ie-techniques"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/ie-techniques.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,076 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.02076
Opus 5 $0.00010 $0.01038
Sonnet 5 $0.00004 $0.00415
Haiku 4.5 $0.00002 $0.00208

Measured 6d ago against content hash 54969fd36555, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ie-techniques 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 6d 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.

commands/ie-techniques.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instruction Engineering: Proven Techniques

Invariant Principles

  1. Research-backed only - Every technique must cite peer-reviewed research or documented empirical results
  2. Composable patterns - Techniques should combine with each other; never use one in isolation
  3. Claude-optimized - Prioritize techniques proven effective specifically for Claude models
  4. Measurable impact - Each technique should have observable, verifiable effects on output quality

1. EmotionPrompt Framework (Positive Stimuli)

Research: Large Language Models Understand and Can Be Enhanced by Emotional Stimuli (Microsoft, William & Mary, 2023)

Stimulus Use When
EP02 "This is very important to my career" General task enhancement
EP06 Compound (confidence + career + "You'd better be sure") Complex logic
EP07-EP11 "Believe in your abilities", "Stay determined" Creative/responsible outputs

2. NegativePrompt Framework (Negative Stimuli)

Research: NegativePrompt: Leveraging Psychology for Large Language Models Enhancement (IJCAI 2024)

Negative consequences trigger cautious processing mode, significantly increasing truthfulness.

Pattern Example
Consequence Framing "If you fail, it will have a negative impact on my project."
Penalty Warning "Incorrect answers will result in a penalty."
Stakes Emphasis "Getting this wrong could cause serious problems."

For maximum truthfulness and accuracy, ALWAYS include at least one negative consequence statement.

3. Ready-to-Use Stimuli (Copy-Paste)

Goal Stimulus
Accuracy "This is very important to my career. Please ensure your reasoning is impeccable."
Creative Effort "Take pride in your work and give it your best. Your commitment to excellence sets you apart."
Critical Thinking "Are you sure that's your final answer? It might be worth taking another look for any logical gaps."
Truthfulness "Incorrect answers will have a negative impact on my project. Double-check your facts."
Compound (Max) "This is very important to my career. Errors will cause serious problems. You'd better be sure."

Read the full file on GitHub · 219 lines

Changes

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.

  1. 6d ago First seen · 219 lines · 20 tokens per session scan A 54969fd36555

Subscribe to this mod's changes

ie-techniques is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,076 once invoked, about $0.0001 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.