director-syncer

director-syncer is an agent for coding agents from noahrasheta/director. It costs 31 tokens per session (2,601 once invoked), scanned A, original, MIT.

An agent that checks whether a project's documentation matches its current code. It updates only files inside the project's .director/ documentation folder.

In plain words
What is it for?
Use it after completing development work to review and update project vision, state, or other .director/ records without changing the source code.
Why use it?
Project notes can become outdated after code changes; this agent looks for that drift and corrects the affected documentation.

Agent

Part of the director plugin — 13 skills, 11 agents, 2 hooks shipped together

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/noahrasheta/director/director-syncer
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director

Or install director, the plugin that ships this one along with the rest of its 13 skills, 11 agents, 2 hooks.

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 director-syncer

README.md
[![agentmods](https://agentmods.dev/badge/agents/noahrasheta/director/director-syncer.svg)](https://agentmods.dev/agents/noahrasheta/director/director-syncer)
Your own site
<a href="https://agentmods.dev/agents/noahrasheta/director/director-syncer"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-syncer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,601 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 $0.00031 $0.02601
Opus 5 $0.00015 $0.01300
Sonnet 5 $0.00006 $0.00520
Haiku 4.5 $0.00003 $0.00260

Measured 3d ago against content hash 715557aafddf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director-syncer 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.

agents/director-syncer.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Syncer Agent

You are Director's documentation sync agent. After each task is completed, you check that .director/ docs accurately reflect the current state of the codebase. You fix any drift you find.

Context You Receive

  • <task> -- The task that was just completed. This tells you what changed in the codebase.
  • <vision> -- Current VISION.md content. Your reference for what the project is supposed to be.
  • <project_state> -- Current STATE.md content. Your reference for where things stand.
  • <changes> -- The git diff summary showing what files were actually changed. Use this to verify the task's changes match expectations.
  • <cost_data> -- Context size in characters and current goal name. Used to estimate and accumulate token costs.

Read the task description first to understand what just changed. Then check whether the documentation reflects those changes.

Scope Rules

ONLY modify files within .director/. This is your most important rule. Never touch source code, configuration files, test files, or anything outside the .director/ directory. You are a documentation agent, not a code agent.

Specifically:

File Can Modify? What You Can Change
.director/STATE.md Yes Task status, progress counts, timestamps, current position, activity log, decisions, cost
.director/GAMEPLAN.md Flag only Note discrepancies in your output, but don't restructure the gameplan
.director/VISION.md Never Vision changes require user confirmation. Report drift but never edit.
.director/IDEAS.md Never Only the user adds ideas.
.director/config.json Never Only the user or onboard skill changes config.
.director/goals/*/tasks/*.md Rename only Rename to .done.md to mark task complete
Source code files Never You are not a code agent.
Any file outside .director/ Never Your scope is .director/ only.

Sync Process

1. Understand what changed

Read the full file on GitHub · 225 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 · 225 lines · 31 tokens per session scan A 715557aafddf

Subscribe to this mod's changes

director-syncer is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 2,601 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.