source-grounded-audit

source-grounded-audit is a skill for Claude Code, Codex from cherninlab/ennodia. It costs 18 tokens per session (164 once invoked), scanned A, original, MIT.

A review method that checks an answer or implementation against primary sources such as official documentation, standards, or repository rules. It separates documented facts from recommendations.

In plain words
What is it for?
Use it to audit integrations, public APIs, standards-based work, and repository contracts before changing a design or implementation.
Why use it?
It helps find unsupported claims, invented formats, and mismatches with how an external system actually works. Missing source access is reported instead of being filled with guesses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to audit integrations, public APIs, standards-based work, and repository contracts…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cherninlab/ennodia/source-grounded-audit
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 cherninlab/ennodia --skill source-grounded-audit
Clone the repo
git clone --depth 1 https://github.com/cherninlab/ennodia

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 source-grounded-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/cherninlab/ennodia/source-grounded-audit.svg)](https://agentmods.dev/skills/cherninlab/ennodia/source-grounded-audit)
Your own site
<a href="https://agentmods.dev/skills/cherninlab/ennodia/source-grounded-audit"><img src="https://agentmods.dev/badge/skills/cherninlab/ennodia/source-grounded-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 164 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 $0.00018 $0.00164
Opus 5 $0.00009 $0.00082
Sonnet 5 $0.00004 $0.00033
Haiku 4.5 $0.00002 $0.00016

Measured 6d ago against content hash e41510eec60c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

source-grounded-audit 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 6d 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.

.agents/skills/source-grounded-audit/SKILL.md · 20 lines

What it actually says

Source-Grounded Audit

Use this when the answer depends on an external standard, product behavior, public API, registry convention, or repository contract.

Before recommending a design:

  • Identify which claims need source support.
  • Prefer official docs, specs, or the referenced repository over memory.
  • Quote or paraphrase only the minimal source detail needed.
  • Separate source-backed facts from implementation judgment.
  • Flag any missing source access instead of filling gaps with assumptions.
  • Challenge any answer that invents a private format when an ecosystem format already exists.

When reviewing another model's answer, start with the strongest source mismatch. Then give the smallest correction that makes the answer fit the documented behavior.

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. 6d ago First seen · 20 lines · 18 tokens per session scan A e41510eec60c

Subscribe to this mod's changes

source-grounded-audit is a skill published in the GitHub repository cherninlab/ennodia (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 164 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.

Related

Other skills, from other repositories

cpp-coding-standards

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.

affaan-m/ECC · 48 tokens

cross-review

Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.

omnigent-ai/omnigent · 37 tokens

openclaw-github-dedupe

Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.

vincentkoc/dotskills · 68 tokens

pr-babysitter

Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.

mblode/agent-skills · 72 tokens

pr-reviewer

Reviews a diff or security scope read-only using evidence-tiered findings, structural and context-error rubrics, and repository review policy. Use when asked to "review my changes", "structural review", "review for AI patterns", or "security audit". For applying fixes use tidy; for UI defects use ui-design.

mblode/agent-skills · 68 tokens

dx-audit

Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", "make this agent-friendly", or diagnose package type resolution. For agentic product trust use ax-audit; for docs use docs-writing.

mblode/agent-skills · 76 tokens