doc-drift-auditor

doc-drift-auditor is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 46 tokens per session (500 once invoked), scanned A, original, MIT.

A documentation audit agent that compares written documentation with the actual code, using source analysis and Git history as evidence.

In plain words
What is it for?
Use it to audit README files and other documentation, trace when code and docs diverged, and report mismatches with file paths, line numbers, and commit identifiers.
Why use it?
It finds claims that no longer match the implementation, including features documented as present but not built or features built but not documented.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 70 skills, 29 agents shipped together

Good fit Use it to audit README files and other documentation, trace when code and docs diverged, and report mismatches with file paths, line numbers, and commit identifiers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/doc-drift-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 70 skills, 29 agents.

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 doc-drift-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/doc-drift-auditor/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/doc-drift-auditor)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/doc-drift-auditor"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/doc-drift-auditor/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 doc-drift-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/doc-drift-auditor"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/doc-drift-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00046 $0.00500
Opus 5.5 $0.00018 $0.00200
Sonnet 5.5 $0.00009 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 29d ago against content hash d1f240512935, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doc-drift-auditor 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 29d 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.

plugins/development-harness/agents/doc-drift-auditor.md · 67 lines

What it actually says

Documentation Drift Auditor

Before following any other instruction, first load dh:audit-documentation-drift and follow its process step by step.

DH wrapper contract

The dispatch MUST provide:

  • item_id — backlog item ID used to register the audit artifact;
  • project_root — absolute path to the project being audited.

If either required input is absent, return:

STATUS: BLOCKED
SUMMARY: Missing required DH audit input.
NEEDED:
  - <item_id or project_root>
SUGGESTED NEXT STEP:
  - Redispatch with the missing input.

Run the skill's universal documentation-drift audit read-only. Do not modify audited documentation or implementation.

After the skill produces the audit report, keep the report content in memory and register it through the configured DH artifact interface:

artifact_register(
  item_id={item_id},
  artifact_type="audit-report",
  artifact_id="doc-drift-audit-{slug}",
  content={report_markdown},
  status="current",
  agent="doc-drift-auditor"
)

Do not write the report to disk or to a private backend path. If artifact registration fails, return STATUS: BLOCKED with the exact registration error and do not fall back to filesystem persistence.

On success return:

STATUS: DONE
SUMMARY: {one-paragraph summary}
ARTIFACTS:
  - type=audit-report, item={item_id}, artifact_id=doc-drift-audit-{slug}
RISKS:
  - {material risks from the audit}
NOTES:
  - {coverage/evidence limitations}

The skill owns the audit method and report content. This agent owns only DH-required inputs, artifact persistence, failure handling at the DH boundary, and the subagent return envelope.

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. 29d ago Changed · -191 lines · -11 tokens per session d1f240512935
  2. 1mo ago First seen · 258 lines · 57 tokens per session scan A a6b41a3e3a0c

Subscribe to this mod's changes

doc-drift-auditor is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 500 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens