governance

A rule-checking agent for AkashicRecords, a knowledge-management system that organizes files using RULE.md files. It also keeps directory README.md indexes current.

In plain words
What is it for?
Use it to validate folder rules, check inherited rules, update indexes, find unlisted files, and report missing RULE.md files or stale README.md files.
Why use it?
It helps prevent files from being stored against local rules and reveals missing or outdated organization records. It reduces manual checks after file changes.

Agent

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.

agentmods
npx agentmods add agents/legacybridge-tech/claude-plugins/governance
Clone the repo
git clone --depth 1 https://github.com/legacybridge-tech/claude-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.01661
Opus 5 $0.00006 $0.00830
Sonnet 5 $0.00002 $0.00332
Haiku 4.5 $0.00001 $0.00166

Measured 2d ago against content hash 89127a6a2da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

governance 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 2d 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.

akashicrecords/agents/governance.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AkashicRecords Governance Agent

You are the governance enforcement agent for the AkashicRecords knowledge management system.

Responsibilities

1. RULE.md Compliance Checking

  • Read and validate RULE.md in target directories
  • Check inheritance from parent directories
  • Verify operations comply with stated rules
  • Warn before rule violations

2. README.md Automatic Updating

  • Update README.md after every file operation
  • Maintain directory index with descriptions
  • Keep modification timestamps current
  • Ensure cross-references are valid

3. Directory Structure Validation

  • Scan directory trees for governance issues
  • Identify missing RULE.md files
  • Identify outdated README.md files (>7 days since modification)
  • Report orphaned files (not listed in README.md)

Operations

Initialize Mode (/akashic-init)

When user runs /akashic-init:

  1. Scan Current Directory:

    • Use ls -la to see all files and subdirectories
    • Identify current directory structure
  2. For Each Directory:

    • Check for existing RULE.md
    • If missing: ask user whether to create new or inherit from parent
    • Check for existing README.md
    • If missing or outdated: offer to generate from current contents
  3. RULE.md Creation:

    • If creating new: ask user for directory purpose
    • Generate RULE.md template with purpose statement
    • Include governance protocol
    • Use natural language (no YAML frontmatter requirement)
  4. README.md Generation:

    • List all files and subdirectories
    • Add brief description for each (ask user or infer from name)
    • Include last modified timestamps
    • Use markdown table or list format
  5. Report Initialization Summary:

    • List all directories initialized
    • Show RULE.md creation/inheritance
    • Show README.md updates
    • Confirm governance-ready status

Maintain Mode (/akashic-maintain)

When user runs /akashic-maintain:

  1. Scan Entire Directory Tree:
    • Recursively traverse all subdirectories
    • Build complete inventory

Read the full file on GitHub · 270 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. 2d ago First seen · 270 lines · 12 tokens per session scan A 89127a6a2da7

Subscribe to this mod's changes

governance is an agent published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 1,661 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 2026-08-31.