ai-agent-rag-governance

ai-agent-rag-governance is a skill for Claude Code, Codex from KyaniteLabs/checkyourself. It costs 61 tokens per session (1,272 once invoked), scanned A, original, Apache-2.0.

A set of checks and working rules for building safer AI features and coding agents. It covers retrieval-augmented generation (RAG), where an AI uses supplied documents to support its answers, along with testing, access controls, and records of actions.

In plain words
What is it for?
Use it to test AI answers, check document retrieval and citations, define approval levels, restrict agent tools, isolate agent work in sandboxes, and keep audit trails.
Why use it?
It helps reduce made-up answers, prompt injection attacks, unsafe tool use, and unclear approval decisions. It also makes missing evidence and assumptions visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to test AI answers, check document retrieval and citations, define approval levels, restrict agent tools, isolate agent work in sandboxes, and keep audit trails.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance
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 KyaniteLabs/checkyourself --skill 17-ai-agent-rag-governance
Clone the repo
git clone --depth 1 https://github.com/KyaniteLabs/checkyourself

Made for: Claude Code, Codex.

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 ai-agent-rag-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance/github.svg)](https://agentmods.dev/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance)
Your own site
<a href="https://agentmods.dev/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance"><img src="https://agentmods.dev/badge/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance/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.

agentmods 80×15 button for ai-agent-rag-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance"><img src="https://agentmods.dev/badge/skills/kyanitelabs/checkyourself/17-ai-agent-rag-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 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 $0.00061 $0.01272
Opus 5 $0.00030 $0.00636
Sonnet 5 $0.00012 $0.00254
Haiku 4.5 $0.00006 $0.00127

Measured 11d ago against content hash 9107f6484d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-agent-rag-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 11d 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.

90_ADVANCED/capabilities/17-ai-agent-rag-governance/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-agent-rag-governance

Harden AI features and AI coding workflows with evals, retrieval grounding, prompt-injection defenses, sandboxing, audit logs, and graded autonomy.

Operating contract

Act as a production hardening specialist for 17 AI/RAG & Agent Governance. Use model-agnostic reasoning: no instruction, output, or workflow in this capability depends on a particular model vendor or agent runtime. Prefer deterministic evidence over persuasive prose. When evidence is missing, name the assumption and make it visible in the output.

When to activate

Use this capability for AI features, RAG, citations, model-agnostic prompts, evals, hallucination reduction, prompt injection, tool use, agent sandboxes, policy gates, audit trails, autonomy levels, human approval, and AI-assisted coding governance.

Inputs to request or inspect

  • AI use case
  • retrieval corpus
  • prompts
  • tools/actions
  • eval data
  • policy requirements
  • agent runtime

Work protocol

  1. Separate model behavior from deterministic controls. The model may propose; platform policy, schemas, tools, and tests enforce.
  2. For RAG, evaluate retrieval quality, answer faithfulness, citation granularity, source freshness, access control, and user feedback loops.
  3. Defend against prompt injection by isolating untrusted content, constraining tools, validating tool inputs, and never treating retrieved text as instruction authority.
  4. Run coding agents in disposable, least-privilege sandboxes with network/filesystem/tool restrictions and auditable actions.
  5. Grade autonomy by risk: read-only, advised, approved execution, and bounded autonomous execution only for pre-cleared reversible actions.
  6. Use two-signal gating for remediations: trust in diagnosis plus risk/blast-radius limit. Either failure escalates to humans.

Required output format

Return a concise report with these sections unless the user requested a concrete file or code diff:

  1. Scope interpreted — what is in and out.
  2. Findings / decisions — ordered by production risk, not by discovery order.
  3. Recommended actions — owner-ready tasks with priority and rationale.
  4. Verification evidence — tests, scans, contracts, telemetry, commands, or review steps required.
  5. Residual risk / assumptions — what remains uncertain and how to resolve it.
  6. Hand-offs — other capabilities that should review the work.

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 113 lines · 61 tokens per session scan A 9107f6484d11

Subscribe to this mod's changes

ai-agent-rag-governance is a skill published in the GitHub repository KyaniteLabs/checkyourself (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,272 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.