coordination

A coordination rule set for multiple agents working in one code workspace. It uses Wolbarg to share briefings, reserve file areas, record findings, and hand work to another agent.

In plain words
What is it for?
Use it before contested work, when editing shared files, while maintaining a claimed area, and when finishing work that another agent may continue.
Why use it?
It reduces overlapping edits and preserves important decisions and discoveries between agents.

Cursor rule

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 rules/wolbarg/cursor/coordination
Clone the repo
git clone --depth 1 https://github.com/wolbarg/cursor
Per session 259 This file is loaded in full into every session.
When invoked 259 The same file — it is already loaded in full.
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 $0.00259 $0.00259
Opus 5 $0.00130 $0.00130
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash 9cceafbf1a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coordination 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.

rules/coordination.mdc · 21 lines

What it actually says

Wolbarg coordination (strict)

Hard requirement: npx wolbarg init must create .wolbarg/config.json before coordination tools work. Reload MCP after init.

Once initialized:

  1. Before contested work, call workspace_briefing with a short query (or no query). If siblings may still be writing, pass wait_ms (e.g. 5000) and/or retry once when hints.retrySuggested is set.
  2. Before editing a hot area, claim_scope with path globs. Conflicts only apply while the other lease is active.
  3. Record durable discoveries with record_finding (dead_end, decision, fact) and useful tags.
  4. Keep presence with pulse_update; renew leases with heartbeat_claim.
  5. On finish, release_claim + create_handoff.

Set WOLBARG_ACTOR_ID to your claim actor_id so hooks don't flag your own exclusive scopes.

Do not rediscover work briefing already surfaces. Prefer non-overlapping scopes when claims conflict.

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 · 21 lines · 259 tokens per session scan A 9cceafbf1a08

Subscribe to this mod's changes

coordination is a cursor rule published in the GitHub repository wolbarg/cursor (0 stars, last pushed 1mo ago), licensed MIT. It adds 259 tokens to every session, about $0.0013 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.