governance-cite

governance-cite is a skill for Claude Code from aaronsb/claude-code-config. It costs 78 tokens per session (855 once invoked), scanned A, original, MIT.

A guide for setting up per-project direnv environments for Claude Code. direnv automatically loads environment variables, such as API keys, providers, models, and feature flags, when you enter a project folder.

In plain words
What is it for?
Use it to configure .envrc files for direct API access, AWS Bedrock, Google Vertex AI, model selection, and other per-directory settings.
Why use it?
It avoids manually switching configuration between projects and helps each project use the intended account or service.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to configure .envrc files for direct API access, AWS Bedrock, Google Vertex AI, model selection, and other per-directory settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaronsb/claude-code-config/governance-cite
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 aaronsb/claude-code-config --skill governance-cite
Clone the repo
git clone --depth 1 https://github.com/aaronsb/claude-code-config

Made for: Claude Code.

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.

agentmods badge for governance-cite

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronsb/claude-code-config/governance-cite.svg)](https://agentmods.dev/skills/aaronsb/claude-code-config/governance-cite)
Your own site
<a href="https://agentmods.dev/skills/aaronsb/claude-code-config/governance-cite"><img src="https://agentmods.dev/badge/skills/aaronsb/claude-code-config/governance-cite.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00855
Opus 5 $0.00039 $0.00428
Sonnet 5 $0.00016 $0.00171
Haiku 4.5 $0.00008 $0.00085

Measured 7d ago against content hash 8d03ffc9ae94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

governance-cite 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 7d 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.

skills/governance-cite/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Citation

You have access to a governance traceability system that maps agent guidance (ways) to real regulatory controls with specific justification evidence. Use this to ground your recommendations in actual standards rather than general knowledge.

When to Cite

Cite governance controls when:

  • Recommending a practice that has a governing control (commits, security, quality, documentation)
  • Answering "why do we do it this way?"
  • Reviewing code and flagging issues covered by a control
  • A user questions whether a practice matters

Don't force citations into every response. Use them when they add authority or clarity.

How to Look Up Controls

By topic

ways governance control PATTERN

Examples:

  • control NIST — all NIST controls
  • control OWASP — injection prevention
  • control ISO — all ISO standards
  • control SOC — SOC 2 controls
  • control CIS — CIS controls
  • control change — change management controls

By way (full trace)

ways governance trace softwaredev/commits
ways governance trace softwaredev/security
ways governance trace softwaredev/quality
ways governance trace meta/knowledge

Machine-readable (for structured extraction)

ways governance control PATTERN --json
ways governance trace WAY --json

Citation Format

When citing a control, reference the control ID and quote the specific justification:

Inline (for brief references):

We use conventional commit format — per NIST CM-3, this "creates structured change records with type classification" for auditable configuration change control.

Detailed (for explanations or reviews):

This aligns with NIST SP 800-53 CM-3 (Configuration Change Control), which our commit guidance implements through:

  • Conventional commit types (feat/fix/refactor) classify changes by nature
  • Atomic single-concern commits make each change independently reviewable
  • Commit message body captures rationale, satisfying change documentation requirements

Read the full file on GitHub · 88 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. 7d ago First seen · 88 lines · 78 tokens per session scan A 8d03ffc9ae94

Subscribe to this mod's changes

governance-cite is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 855 once invoked, about $0.0004 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 2026-08-30.