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/review-plan-behavior)<a href="https://agentmods.dev/commands/axiomantic/spellbook/review-plan-behavior"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-behavior/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/review-plan-behavior"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/review-plan-behavior.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 | $0.00013 | $0.00838 |
| Opus 5 | $0.00006 | $0.00419 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
review-plan-behavior 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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 3: Behavior Verification Audit
Invariant Principles
- Inferred behavior is not verified behavior - Method names suggest intent; only source confirms it
- Fabrication is the root failure - Invented parameters or return types cascade into debugging loops
- Every code reference needs file:line - Plans citing existing code without source location are unverified
The Fabrication Anti-Pattern
# FORBIDDEN: The Fabrication Loop
1. Plan assumes method does X based on name
2. Agent writes code, fails because method actually does Y
3. Agent INVENTS parameter: method(..., partial=True)
4. Fails because parameter doesn't exist
5. Agent enters debugging loop, never reads source
6. Hours wasted on fabricated solutions
# REQUIRED in Plan
1. "Behavior verified by reading [file:line]"
2. Actual method signatures from source
3. Constraints discovered from reading source
4. Executing agents follow verified behavior, no guessing
Dangerous Assumption Patterns
Flag when plan exhibits any of:
1. Assumes convenience parameters exist:
- "Pass
partial=Trueto allow partial matching" (VERIFY THIS EXISTS) - "Use
strict_mode=Falseto relax validation" (VERIFY THIS EXISTS)
2. Assumes flexible behavior from strict interfaces:
- "The test context allows partial assertions" (VERIFY: many require exhaustive assertions)
- "The validator accepts subset of fields" (VERIFY: many require complete objects)
3. Assumes library behavior from method names:
- "The
update()method will merge fields" (VERIFY: might replace entirely) - "The
validate()method returns errors" (VERIFY: might raise exceptions)
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.
- 5d ago First seen · 97 lines · 13 tokens per session scan A 6ecdcc22f214
review-plan-behavior is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 838 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
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
code-quality-plan-creator
LSP-powered architectural code quality analysis - works with any executor (loop or swarm).
mr-description-creator
Generate and apply MR/PR description directly via gh or glab CLI (project).
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
pr-review
Generate a PR review report aggregating quality scan, coverage, complexity, and breaking changes.