docs-sync

A command for finding documentation that may be out of date after code changes.

In plain words
What is it for?
Use it to identify stale API, database, deployment, architecture, stack, or coding-guideline documents and ask which updates to apply.
Why use it?
It compares changes since the last documentation update and maps affected code to the relevant rules and reference pages.

Command 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 commands/jondarza/loadout/docs-sync
Clone the repo
git clone --depth 1 https://github.com/JOndarza/loadout

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 354 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 $0.00013 $0.00354
Opus 5 $0.00006 $0.00177
Sonnet 5 $0.00003 $0.00071
Haiku 4.5 $0.00001 $0.00035

Measured 2d ago against content hash 59320437b678, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 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.

.claude/skills/docs-architect/assets/commands/docs-sync.md · 22 lines

What it actually says

Run the docs-architect skill in sync mode.

  1. Find the last commit that touched docs/ or .claude/rules/: git log --oneline --all -- docs/ .claude/rules/ | head -1
  2. List all files changed since that commit: git diff --name-only <last>..HEAD
  3. Delegate the file-change analysis to the doc-explorer subagent (isolated context) if the list is longer than 20 files.
  4. Map changed code files to affected docs and rules:
    • *.csproj, package.json, Cargo.toml.claude/rules/tech-stack.md + docs/tech-stack.md
    • docker-compose*, Dockerfile*, .env*docs/deployment.md
    • Controllers / routes / endpoints → .claude/rules/api.md + docs/api-contracts.md
    • Entities / migrations → .claude/rules/database.md + docs/database-schema.md
    • Domain layer / patterns / middleware → .claude/rules/architecture.md + docs/architecture.md
    • Naming / validators / test files → .claude/rules/coding-rules.md + docs/coding-rules.md
  5. Output a sync report listing docs-needing-update vs. docs-still-current.
  6. Ask the user: update affected docs now? [yes / pick individually / skip]
  7. If yes, update each affected rule AND doc file (dual update).
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 · 22 lines · 13 tokens per session scan A 59320437b678

Subscribe to this mod's changes

docs-sync is a command published in the GitHub repository JOndarza/loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 354 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.