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.
git 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/commands/axiomantic/spellbook/ie-techniques)<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.
<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>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 | $0.00020 | $0.02076 |
| Opus 5 | $0.00010 | $0.01038 |
| Sonnet 5 | $0.00004 | $0.00415 |
| Haiku 4.5 | $0.00002 | $0.00208 |
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.
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
- Research-backed only - Every technique must cite peer-reviewed research or documented empirical results
- Composable patterns - Techniques should combine with each other; never use one in isolation
- Claude-optimized - Prioritize techniques proven effective specifically for Claude models
- 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." |
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.
- 6d ago First seen · 219 lines · 20 tokens per session scan A 54969fd36555
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.
Other commands, from other repositories
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
add-command
Add a new slash command to the current plugin.