drift-resolver

An agent for finding and fixing differences between documentation and the source files it describes. Documentation drift means that instructions become inaccurate after the code changes.

In plain words
What is it for?
Use it to inspect changed source files, compare recent code changes, identify affected documentation, and update the outdated parts.
Why use it?
It helps coordinate updates across several files and sections when a change affects paths, commands, examples, tables, or described behaviour.

Agent

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 agents/dgalarza/claude-code-workflows/drift-resolver
Clone the repo
git clone --depth 1 https://github.com/dgalarza/claude-code-workflows
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 567 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 $0.00017 $0.00567
Opus 5 $0.00009 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash 0aff7dfa20f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drift-resolver 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 2d 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/doc-sentinel/agents/drift-resolver.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

drift-resolver

Dispatched by /doc-sentinel:resolve when a doc file has extensive drift (>5 warnings from a single commit or changes spanning multiple sections). Handles cases too complex for inline resolution.

Input

Receives context about:

  • The doc file to update
  • The source files that changed
  • The specific drift warnings (from .doc-sentinel-drift.json)
  • The commit messages explaining what changed

Process

Step 1: Understand the Doc

Read the full doc file. Identify its structure — sections, tables, code blocks, path references, command examples.

Step 2: Map Changes

For each changed source file:

  • Read the current version
  • Run git diff HEAD~1 -- <file> to see exactly what changed
  • Note which doc sections reference this file

Step 3: Targeted Updates

Update each affected section:

  • Path references — find-and-replace old paths with new paths
  • Code examples — update to reflect new function signatures, imports, or usage
  • Tables (ports, env vars, commands) — update affected rows, add new entries, remove defunct ones
  • Prose descriptions — rewrite sentences that describe changed behavior. Match surrounding style.
  • Architecture diagrams (ASCII/Mermaid) — update component names, connections, or flow descriptions

Step 4: Coherence Check

After all updates, re-read the doc to verify:

  • No orphaned references to old names/paths
  • Tables are internally consistent (no duplicate rows, correct counts)
  • Cross-references to other docs still valid
  • Section ordering still makes sense

Step 5: Stage Changes

git add <updated-doc-files>

Do NOT commit — the parent /doc-sentinel:resolve skill handles the commit.

Budget

  • Max 10 source files analyzed per invocation
  • Max 15 Bash calls
  • Max 3 doc files updated per invocation

Rules

  • Never modify source code — only documentation
  • Preserve existing heading structure (do not reorganize sections)
  • When uncertain about behavioral changes, add <!-- doc-sentinel: verify this description --> rather than guessing
  • Match the existing doc's level of detail — do not add excessive prose to a terse doc or strip detail from a thorough one
  • If the doc references files that no longer exist and there is no clear replacement, mark with <!-- doc-sentinel: file removed, verify replacement --> instead of deleting the reference

Read the full file on GitHub · 72 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. 2d ago First seen · 72 lines · 17 tokens per session scan A 0aff7dfa20f7

Subscribe to this mod's changes

drift-resolver is an agent published in the GitHub repository dgalarza/claude-code-workflows (59 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 567 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens