code-doc-drift-audit

code-doc-drift-audit is a skill for Claude Code, Codex from Detective-XH/DocGraph. It costs 62 tokens per session (948 once invoked), scanned A, original, MIT.

An advisory audit that compares documentation with source code to find undocumented files, broken links, and documents without code references.

In plain words
What is it for?
Use it in a project with the codedoc domain pack enabled to review documentation gaps and possible documentation-code drift.
Why use it?
It highlights documentation that may no longer match the code, without automatically changing code or making policy decisions.

Skill for Claude CodeCodex

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 skills/detective-xh/docgraph/code-doc-drift-audit
Any agent
npx skills add Detective-XH/DocGraph --skill code-doc-drift-audit
Clone the repo
git clone --depth 1 https://github.com/Detective-XH/DocGraph

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 code-doc-drift-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/detective-xh/docgraph/code-doc-drift-audit.svg)](https://agentmods.dev/skills/detective-xh/docgraph/code-doc-drift-audit)
Your own site
<a href="https://agentmods.dev/skills/detective-xh/docgraph/code-doc-drift-audit"><img src="https://agentmods.dev/badge/skills/detective-xh/docgraph/code-doc-drift-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 948 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 $0.00062 $0.00948
Opus 5 $0.00031 $0.00474
Sonnet 5 $0.00012 $0.00190
Haiku 4.5 $0.00006 $0.00095

Measured 4d ago against content hash 3f5ccbcb6d5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-doc-drift-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 4d 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/code-doc-drift-audit/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.

Docs-Code Drift Audit

Invocation — Claude Code: Skill("code-doc-drift-audit") | OpenCode / Codex: use triggers above.

Runs the DocGraph docs-code drift audit and presents findings for human review. The audit is advisory — findings highlight candidates for action, not authoritative rulings.

Execution

  • Model: Haiku (query) → Sonnet (remediation suggestions if requested)
  • Effort: Low
  • Advisor: Not required
  • Core computation: done by DocGraph's GetDriftFindings engine, not by this skill

Step 1: Check prerequisites

docgraph_status

Confirm:

  • code_doc pack is listed under Domain Packs and is enabled
  • At least one code_file node is indexed (check node count or run docgraph_search kind=code_file)

If code_doc is not enabled, tell the user to run:

docgraph pack enable code_doc <project-path>
# or for workspace mode:
docgraph pack enable --workspace code_doc <workspace-path>

Then wait for the sync to complete before proceeding.


Step 2: Run the drift audit

docgraph_context task="docs-code drift audit" format=drift_audit

This calls DocGraph's GetDriftFindings engine, which checks (code_doc findings only):

Code Severity Meaning
code.missing_symbol warning A doc links to a code file path that is not indexed — broken doc-to-code reference
code.undocumented_export info A code file has no incoming references, wikilinks_to, or related_to edges from any doc — no documentation points to it
code.unanchored_feature info An approved or review-status doc has no outgoing edge to any indexed code file — feature doc not connected to implementation

If code_doc is disabled, the output will show zero code.* findings regardless of repo content.


Step 3: Present findings to the user

Group findings by code, severity first (warnings before info).

For each finding:

  1. State the file path(s) and finding code
  2. Show the message and evidence from the finding
  3. Suggest a concrete remediation (below) — but do NOT make the change without confirmation

Read the full file on GitHub · 113 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. 4d ago First seen · 113 lines · 62 tokens per session scan A 3f5ccbcb6d5e

Subscribe to this mod's changes

code-doc-drift-audit is a skill published in the GitHub repository Detective-XH/DocGraph (7 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 948 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.

Related

Other skills, from other repositories

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

ingest-l1

L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…

Gixsy95/abap_wiki · 91 tokens

research-l2

Executes Phases 1-3 of the L2 process of the abapwiki knowledge base on a slice: launches the abap-functional-researcher sub-agent (gap discovery + multi-source auto-research: wiki -> raw/docs -> MCP abap-fs on the system read-only -> standard knowledge), ingests gaps and evidence, and generates questionnaires for…

Gixsy95/abap_wiki · 115 tokens

slice-init

Creates an L2 slice in the abapwiki knowledge base: a business process on which to build functional documentation. Writes the manifest (curated anchors + mandatory real owner) and derives the membership from the dependency graph (BFS hop<=2). Use this skill to start the L2 process on a custom domain. Does not promote…

Gixsy95/abap_wiki · 86 tokens

capture-answer

Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…

Gixsy95/abap_wiki · 88 tokens

ingest-l0

L0 bootstrap of the abapwiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.

Gixsy95/abap_wiki · 64 tokens