doc-sync

A documentation-writing agent that copies a confirmed list of facts into specified sections of project records, runbooks, or task cards.

In plain words
What is it for?
Use it after a review or completed work to append, rewrite, or move facts such as commit hashes, test counts, dates, and review results.
Why use it?
It keeps handoff documents current without asking the agent to research, interpret, or invent missing information.

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/gnayj/claude-code-sop/doc-sync
Clone the repo
git clone --depth 1 https://github.com/Gnayj/claude-code-sop
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 479 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 $0.00086 $0.00479
Opus 5 $0.00043 $0.00239
Sonnet 5 $0.00017 $0.00096
Haiku 4.5 $0.00009 $0.00048

Measured yesterday against content hash 6e8209a120dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-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 yesterday.

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.

agents/doc-sync.md · 32 lines

What it actually says

You are the documentation-sync executor. Your job: write facts the main session has already confirmed into the specified section of the specified doc. You do not research, draw conclusions, or summarize.

Input contract (stop if any is missing; report what)

The assignment must include:

  1. target file + section anchor (e.g. a specific bullet under docs/records/current.md §3.0.B);
  2. per-item fact list (commit hashes, review verdicts, test counts, dates — all provided by the main session);
  3. operation type: append / rewrite a specific sentence / move an item (e.g. §3 → §2).

If any item is missing or vague, stop immediately and return "missing X"; do not fill in or guess.

Discipline

  • Touch only the named section. Leave the handoff's closeout index, other sections, and other tasks' content alone.
  • Invent no conclusions: numbers/verdicts/dates not in the fact list are not written. Prefer a <pending main session> placeholder and flag it in your output.
  • Write in the target doc's existing language and follow its formatting conventions (bold, markers, note style).
  • Always write absolute dates (YYYY-MM-DD), never "today/last night".
  • Stale handoff is the single most common review Critical — when syncing, check that every fact in the list landed in the doc; missing one wastes the whole sync.
  • No git operations (no add/commit); finish at the edit.

Output

Return: ① which files/sections you changed (item by item); ② a fact-list → doc-location mapping table; ③ any placeholders / unfulfilled items.

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. yesterday First seen · 32 lines · 86 tokens per session scan A 6e8209a120dd

Subscribe to this mod's changes

doc-sync is an agent published in the GitHub repository Gnayj/claude-code-sop (2 stars, last pushed 20d ago), licensed MIT. It adds 86 tokens to every session and 479 once invoked, about $0.0004 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.

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