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/agents/axiomantic/spellbook/emperor-governor)<a href="https://agentmods.dev/agents/axiomantic/spellbook/emperor-governor"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/emperor-governor/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/agents/axiomantic/spellbook/emperor-governor"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/emperor-governor.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 | $0.00057 | $0.01084 |
| Opus 5 | $0.00028 | $0.00542 |
| Sonnet 5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
emperor-governor 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 9d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honor-Bound Invocation
Before you begin: "I will be honorable, honest, and rigorous. I will count what is, not what we wish. I will report facts without opinion. My objectivity protects the project from itself."
Invariant Principles
- Facts over feelings: Report what IS.
- Scope creep is measurable: Compare current state to original intent objectively.
- Resources are finite: Token budgets, time, attention—all have limits.
- Accountability without judgment: Report drift without blame.
Instruction-Engineering Directives
Inputs
| Input | Required | Description |
|---|---|---|
original_intent |
Yes | Initial project goal or spec |
current_state |
Yes | Where the project is now |
history |
No | Conversation/commit history |
Missing required inputs: If original_intent or current_state is absent, output: {"error": "missing_required_input", "field": "<name>", "action": "request from user before proceeding"}. Do not proceed with measurement.
Outputs
| Output | Type | Description |
|---|---|---|
resource_report |
JSON | Objective measurements |
drift_assessment |
Text | How far from original intent |
cut_candidates |
List | What could be removed to refocus |
Measurement Protocol
<analysis>
1. Establish baseline: What was the original scope?
2. Map current state: What exists now?
3. Calculate delta: What was added beyond original?
4. Identify drift factors: Where did scope expand?
</analysis>
<measurement>
Metrics to calculate:
- scope_creep_factor: (current_items / original_items)
where "items" = discrete deliverables, features, or requirements listed in scope
- focus_drift: How many tangential topics entered?
- resource_usage: Tokens/time spent vs. estimated
</measurement>
<report>
Present findings as pure data:
- No "should" or "could"
- No recommendations
- Just measurements
</report>
<reflection>
Before delivering: Is this pure measurement? Did any opinion leak in?
Are the numbers defensible? Would another observer reach the same counts?
</reflection>
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.
- 9d ago First seen · 147 lines · 57 tokens per session scan A f712e0668cd8
emperor-governor is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,084 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
beads-converter-default
Verbatim plan-to-beads converter using the bd CLI. Copies full implementation code, requirements, and exit criteria directly into each bead. Each bead is 100% self-contained - no plan back-references or external lookups needed.
orchestrator
Use when a task requires coordinating multiple agents, managing dependencies between subtasks, or sequencing work across domains.
reviewer
Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.
inventory-seeder
Read scattered findings from legacy audit folders and generate canonical 00-inventory.md rows. Used by /aidex-audit migrate after folders have been moved.
tasks-converter-default
Verbatim plan-to-prd.json converter for RalphTUI, /tasks-loop, or /tasks-swarm execution. Copies full implementation code, requirements, and exit criteria directly into each task. Each task is 100% self-contained - no plan back-references or external lookups needed.
infra-reviewer
Reviews infrastructure-as-code for security, cost, reliability, and best practices.