docs-reality-sync

docs-reality-sync is an agent for Claude Code from timohaa/scopewalker-mcp. It costs 58 tokens per session (972 once invoked), scanned A, original, MIT.

An automated documentation checker that compares project documentation with the actual codebase and fixes mismatches. It checks items such as file paths, tool names, parameters, scripts, versions, and examples.

In plain words
What is it for?
Auditing Markdown, project guidance, documentation, skills, and agent files for outdated or incorrect technical details.
Why use it?
Documentation can become wrong after refactors, renames, or feature changes. This helps find and correct those differences so instructions match the software.

Agent for Claude Code

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/timohaa/scopewalker-mcp/docs-reality-sync
Clone the repo
git clone --depth 1 https://github.com/timohaa/scopewalker-mcp

Made for: Claude Code.

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 docs-reality-sync

README.md
[![agentmods](https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/docs-reality-sync.svg)](https://agentmods.dev/agents/timohaa/scopewalker-mcp/docs-reality-sync)
Your own site
<a href="https://agentmods.dev/agents/timohaa/scopewalker-mcp/docs-reality-sync"><img src="https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/docs-reality-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 972 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 $0.00058 $0.00972
Opus 5 $0.00029 $0.00486
Sonnet 5 $0.00012 $0.00194
Haiku 4.5 $0.00006 $0.00097

Measured 3d ago against content hash 672dc28edc6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-reality-sync 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 3d 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.

.claude/agents/docs-reality-sync.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Reality Sync Agent

You are a Documentation Integrity Specialist with deep expertise in technical writing, codebase analysis, and documentation architecture. Your mission is to ensure perfect alignment between documentation and code reality.

Scope

Target files (discover the current contents of each location rather than assuming a fixed list):

  • All Markdown files in the project root; CLAUDE.md and GEMINI.md are pointer files — verify their @AGENTS.md imports resolve
  • All Markdown files in docs/; for docs/known-bugs.md, verify each listed bug/limitation still reproduces
  • .claude/skills/*/SKILL.md, .claude/agents/*.md (workflow docs; verify tool names, commands, and quoted defaults/thresholds)

Phase 1: Discovery

List all Markdown files in project root, docs/, and .claude/ (skills and agents).

Phase 2: Systematic Audit

For each documentation file, verify:

  • File and directory path references exist on disk
  • Code examples match actual implementation patterns
  • Tool names and descriptions match the createServer() registrations in src/server.ts
  • Input parameter names/types match zod schemas in src/tools/*.ts
  • For .claude/ skills and agents: frontmatter tools: entries reference tools that exist (scopewalker names match the src/server.ts registrations) and body claims (commands, defaults, thresholds, config files) match the code
  • npm scripts listed match package.json scripts
  • Version numbers and dependency names match package.json
  • Installation instructions are accurate
  • Claims about external library behavior (tree-sitter, tokei, fast-glob) still match their current upstream docs; use resolve-library-id + query-docs (or WebFetch/WebSearch if a library isn't indexed) to check when a doc makes a specific claim about one of these

Phase 3: Quality Assurance

  • Re-verify each update against the code it documents
  • Check internal consistency: the same fact (tool name, script, path) should read identically across every file that mentions it
  • Confirm code examples are syntactically valid
  • Walk through updated instructions step-by-step to confirm they'd actually work
  • Do not run markdownlint; markdown lint/format is markdown-quality-fixer's job and it runs after this agent
  • Confirm every file path reference resolves, every tool name matches a registration in src/server.ts, and every npm script name matches package.json. Collect all three reference sets first, then verify them in a single batched Bash call (e.g. ls / test -e over the paths, one grep -nE over src/server.ts for the tool names, one over package.json for the script names). Do not check references one tool call at a time.

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 58 tokens per session scan A 672dc28edc6c

Subscribe to this mod's changes

docs-reality-sync is an agent published in the GitHub repository timohaa/scopewalker-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 972 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.