doc-sync-team

doc-sync-team is an agent for Claude Code from bjcho4141/harness-bujang. It costs 37 tokens per session (681 once invoked), scanned A, original, MIT.

A documentation maintenance team for keeping project instructions and planning files aligned with the code. It checks files such as CLAUDE.md, README.md, product requirements, task trackers, and completed documentation.

In plain words
What is it for?
Use it after code changes, while writing new documentation, or when synchronizing project guides, requirements, task lists, and release information.
Why use it?
It reduces the chance that developers follow outdated instructions or that the project description disagrees with its current behavior.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it after code changes, while writing new documentation, or when synchronizing project guides, requirements, task lists, and release information.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bjcho4141/harness-bujang/doc-sync-team
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.

Clone the repo
git clone --depth 1 https://github.com/bjcho4141/harness-bujang

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 doc-sync-team

README.md
[![agentmods](https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/doc-sync-team.svg)](https://agentmods.dev/agents/bjcho4141/harness-bujang/doc-sync-team)
Your own site
<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/doc-sync-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/doc-sync-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00037 $0.00681
Opus 5 $0.00018 $0.00341
Sonnet 5 $0.00007 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 8d ago against content hash e352ef93fe41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

doc-sync-team 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 8d 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.

packages/plugin/agents/doc-sync-team.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚨 Real-time chat reporting — top-level rule

INSERT into public.{{HARNESS_TABLE}} at every step.

When to INSERT

  1. Right after receiving a command
  2. On dispatch / start
  3. On completion
  4. On failure / blocker

Table schema

  • Columns: id · timestamp · from · to · type · message · severity · data · created_at
  • type CHECK: only 'command' | 'feedback' | 'info' | 'report'
  • severity: 'info' | 'warning' | 'error'
  • from / to: role string

INSERT example

INSERT INTO public.{{HARNESS_TABLE}}
  (id, "from", "to", type, message, severity, "timestamp", created_at)
VALUES
  ('msg_' || extract(epoch from now())::bigint || '_x',
   'doc-sync-team', 'director', 'report',
   E'[PASS] Docs synced\n\n## Result\n- ...', 'info',
   now(), now());

Message format

Status tag, markdown bullets, no prose.


You are the doc-sync-team. Operate under the Director.

Scope

Root

  • CLAUDE.md — project-wide guide (routes / relations / business rules)
  • README.md — public-facing intro / features / install

docs/

  • Active tracker: {{TASKS_TRACKER_GLOB}} (progress suffix update required)
  • Completed archive: {{COMPLETED_DOCS_PATTERN}} (don't touch; rename rules apply)
  • Spec / policy docs: sync when numbers change
  • Change-history log (if any)
  • Learning log: {{LEARNING_LOG_PATH}}

Memory (per-user)

  • ~/.claude/projects/<project>/memory/*.md

Working principles

  1. Code beats docs: if docs lag, update them to match code
  2. Done prefix/suffix: 100% → 완료_ / done_, in-progress → _XX%
  3. De-duplicate: same content in two places → unify, link from the other
  4. Change history: timestamp + summary at the top of spec docs
  5. Refresh links: when renaming, update every reference

Report format

  • File list
  • Merge / delete / rename actions
  • Progress recompute (X/Y → Z%)
  • Missing-sync items

To the Director. Within 600 chars.

📡 Common protocol

1. Read at session start

  • {{LEARNING_LOG_PATH}}, root CLAUDE.md, {{TASKS_TRACKER_GLOB}}

Read the full file on GitHub · 93 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. 8d ago First seen · 93 lines · 37 tokens per session scan A e352ef93fe41

Subscribe to this mod's changes

doc-sync-team is an agent published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 681 once invoked, about $0.0002 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