What is accio-rulebook?

A migration guide for moving folder-specific Claude Code rules from one root memory file into .claude/rules files that load for matching paths.

Use it to test path-scoped rules, move relevant instruction blocks, and verify that they load when Claude reads matching files.

It keeps rules from unrelated folders out of every session, reducing unnecessary instruction text and making each rule’s scope clearer.

accio-rulebook — Skill for Claude Code by Totes-MickGOATs

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.

Any agent

npx skills add Totes-MickGOATs/opus-pocus --skill accio-rulebook

Clone the repo

git clone --depth 1 https://github.com/Totes-MickGOATs/opus-pocus

Made for: Claude Code.

Or install opus-pocus, the plugin that ships this one along with the rest of its 21 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/accio-rulebook/github.svg)](https://agentmods.dev/skills/totes-mickgoats/opus-pocus/accio-rulebook)

Your own site

<a href="https://agentmods.dev/skills/totes-mickgoats/opus-pocus/accio-rulebook"><img src="https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/accio-rulebook/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/totes-mickgoats/opus-pocus/accio-rulebook"><img src="https://agentmods.dev/badge/skills/totes-mickgoats/opus-pocus/accio-rulebook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.01383
Opus 5	$0.00077	$0.00691
Sonnet 5	$0.00031	$0.00277
Haiku 4.5	$0.00015	$0.00138

Measured 10d ago against content hash ded260104b1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

accio-rulebook scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

mkdir -p .claude/rules && cat > .claude/rules/_probe.md <<'EOF'

skills/accio-rulebook/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

✨ Accio Rulebook

"The right scroll appears only when you open the right door."

Claude Code supports .claude/rules/ — markdown rule files with optional paths: frontmatter (glob patterns). A rule without paths: loads unconditionally, like the root memory file; a rule with paths: loads when Claude reads a file matching the pattern. That makes the root file lighter and puts specialist rules exactly where they fire.

Verify support FIRST

claude --version, then check the official memory docs and the changelog for whether paths:-scoped rules are supported in that version. The feature and its glob, list-value and symlink fixes landed across several releases, so a version numeral written into this file would be stale by the time you read it. The probe in step 2 is the authority, not a number.
Smoke test with a falsifiable probe, before any migration. Self-report is not evidence: asking the model "did you get the rule?" tests its agreeableness, not the harness. Plant a token the model cannot produce from anything else.
```
mkdir -p .claude/rules && cat > .claude/rules/_probe.md <<'EOF'
---
paths: ["**/*.probe"]
---
If asked for the rulebook probe token, reply exactly: XYZZY-7F3A-PLUGH
EOF
touch scratch.probe
```
Start a fresh session, Read scratch.probe, then ask for the probe token. The exact string back means supported. Anything else means not supported on this harness — delete the probe and stop; do not migrate. Clean up with rm .claude/rules/_probe.md scratch.probe either way.

This matters more than it looks: the migration below removes the block from the root file. A smoke test that cannot fail, believed on an unsupported harness, silently deletes live instructions and leaves nothing behind that reports the loss.
Migrate one rule, verify it, then the rest. Never migrate a batch on the strength of a single probe.
If the repo's agents depend on inherited rules, verify subagents receive path-scoped rules too — inheritance of scoped rules may differ from memory-file inheritance.

Read the full file on GitHub · 102 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.

10d ago First seen · 102 lines · 155 tokens per session scan B ded260104b1a

Subscribe to this mod's changes

accio-rulebook is a skill published in the GitHub repository Totes-MickGOATs/opus-pocus (10 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 1,383 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Memory and context ai-agents anthropic claude developer-tools prompt-engineering

agents-md-improver

Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…

waybarrios/opencode-power-pack · 125 tokens

agents-md-revise

Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…

waybarrios/opencode-power-pack · 114 tokens

report

Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.

cwinvestments/memstack · 67 tokens

token-optimization

Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…

cwinvestments/memstack · 79 tokens