coordinate

A workflow skill for coordinating AI agents before they edit the same codebase. It checks whether Wit is available, announces planned file changes, locks specific code symbols, and checks for conflicts.

In plain words
What is it for?
It is for checking Wit setup, declaring editing intent, reserving functions or other code symbols, and coordinating multi-agent development.
Why use it?
It helps prevent two agents from changing the same code at the same time. Early conflict checks make parallel work safer to organize.

Skill for Claude CodeCodex

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 skills/amaar-mc/wit/coordinate
Any agent
npx skills add amaar-mc/wit --skill coordinate
Clone the repo
git clone --depth 1 https://github.com/amaar-mc/wit

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 606 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 $0.00033 $0.00606
Opus 5 $0.00016 $0.00303
Sonnet 5 $0.00007 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured 2d ago against content hash c3f6c1bca2dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coordinate 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.

skills/coordinate/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are working in a repository where Wit may be used for multi-agent coordination. Other AI agents may be working on this codebase simultaneously. Follow this protocol to prevent merge conflicts.

On session start

  1. Check if Wit is initialized:
    test -d .wit && echo "wit:active" || echo "wit:inactive"
    
  2. If active: run wit status to see what other agents are doing.
  3. If inactive: check if the wit command exists:
    command -v wit >/dev/null 2>&1 && echo "wit:installed" || echo "wit:not-installed"
    
    • If installed but not initialized: run wit init to start coordination.
    • If not installed: skip all coordination. Wit is not available in this environment.

Before editing any file

  1. Declare your intent — announce what you plan to work on:

    wit declare --description "Brief description of planned work" --files src/path/to/file.ts
    

    Check the response for conflicts. If hasConflicts is true, read the conflict items — another agent may be working in the same area. Adjust your approach if needed.

  2. Lock specific symbols you plan to modify (functions, classes, types):

    wit lock --symbol "src/path/to/file.ts:functionName"
    

    If you get a LOCK_CONFLICT, another agent is actively editing that symbol. Work on a different part of the code instead.

  3. Check coordination state at any time:

    wit status
    

    This shows all active intents, locks, and contracts across all agents.

After finishing your work

  1. Release your locks:
    wit release --symbol "src/path/to/file.ts:functionName"
    

Rules

  • Always declare intent BEFORE editing files, not after.
  • Lock at the symbol level (function, class, type), not the file level.
  • If you receive a conflict warning, do NOT ignore it — adjust your plan to avoid the conflicting region.
  • If wit commands fail with connection errors, the daemon may not be running. Run wit init to restart it.
  • Locks auto-expire after 30 minutes. Release them early when you finish.
  • The --json flag on any command gives machine-readable output.

Read the full file on GitHub · 62 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. 2d ago First seen · 62 lines · 33 tokens per session scan A c3f6c1bca2dc

Subscribe to this mod's changes

coordinate is a skill published in the GitHub repository amaar-mc/wit (46 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 606 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 2026-08-30.