A command for keeping the project's main documentation aligned with the code. It refreshes marked sections describing code facts, while leaving human-written explanations untouched.

Previewing or applying documentation synchronization, reviewing affected explanations, and checking the result with a documentation guard.

Documentation becomes unreliable when details such as endpoints, database entities, screens, dependencies, or environment variables change. This command updates those facts and points out nearby prose that may need review.

sync — Command by raccioly

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/raccioly/docguard/sync

Clone the repo

git clone --depth 1 https://github.com/raccioly/docguard

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 508 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.00508
Opus 5	$0.00010	$0.00254
Sonnet 5	$0.00004	$0.00102
Haiku 4.5	$0.00002	$0.00051

Measured 2d ago against content hash 065d8cb2f4b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

extensions/spec-kit-docguard/commands/sync.md · 63 lines

What it actually says

DocGuard Sync

Keep the documentation memory ALWAYS UP TO DATE. Sync re-derives every code-truth section (endpoints, entities, screens, tech stack, env vars) and refreshes the matching source=code sections of existing canonical docs in place. Human prose is never touched — it lives outside markers or in source=human sections.

When a code section changes, the prose sections in that doc are flagged for agent review.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Execution

Preview what will change (dry run, never writes):

npx --yes docguard-cli@latest sync $ARGUMENTS

If only source=code sections are stale, apply the mechanical refresh:

npx --yes docguard-cli@latest sync --write $ARGUMENTS

For each "prose to review" line, read the affected doc and update the surrounding human-written section to match the new code reality (e.g. if the endpoints table grew, update the API overview prose). Then re-run guard:

npx --yes docguard-cli@latest guard

Flags

--since <ref> — also report which code files changed since this git ref (context for prose updates).
--write — apply the mechanical refreshes. Default is a dry-run preview.
--force — sync docs even without the  marker.
--format json — machine-readable output (updates, reviews, skipped).

When to use

Before opening a PR: docguard sync --since main to refresh any stale sections.
On a pre-commit hook: auto-keep the memory current.
After a big refactor: confirm the doc map still matches the territory.

Triage glyphs

↻ mechanically refreshed (code section updated)
• stale (will refresh with --write)
🤖 prose to review — open the doc, update the relevant human-written section

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.

2d ago First seen · 63 lines · 19 tokens per session scan A 065d8cb2f4b8

Subscribe to this mod's changes

sync is a command published in the GitHub repository raccioly/docguard (27 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 508 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.

Planning Writing and docs ai-agents cdd cli documentation drift-detection eu-ai-act

sync

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

DocGuard Sync

User Input

Execution

Flags

When to use

Triage glyphs

What this file has done since we first saw it

Other commands, from other repositories

review-renovate

monitor-ci

/add-claude-rule

implement-regression-tests

plan-regression-tests

ado-pull