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.
npx agentmods add skills/wolbarg/cursor/wolbarg-coordinationnpx skills add wolbarg/cursor --skill wolbarg-coordinationgit clone --depth 1 https://github.com/wolbarg/cursorWrote 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.
[](https://agentmods.dev/skills/wolbarg/cursor/wolbarg-coordination)<a href="https://agentmods.dev/skills/wolbarg/cursor/wolbarg-coordination"><img src="https://agentmods.dev/badge/skills/wolbarg/cursor/wolbarg-coordination.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00072 | $0.00593 |
| Opus 5 | $0.00036 | $0.00296 |
| Sonnet 5 | $0.00014 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
wolbarg-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 4d 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.
What it actually says
Wolbarg Coordination
Hard prerequisite — wolbarg init
npx wolbarg init
If tools return WOLBARG_NOT_INITIALIZED, init then reload MCP. Skipping init is not supported.
Workflow
1. Brief (race-aware)
workspace_briefing
query: "auth" # keep SHORT (1–3 tokens)
wait_ms: 5000 # when siblings may still be writing
min_findings: 1 # optional soft-sync thresholds
min_active_claims: 0
min_handoffs: 0
Or omit query for a full snapshot.
Read hints.retrySuggested / hints.messages. If briefing is empty and parallel agents are expected, retry once with wait_ms rather than assuming the store is blank.
Conflict with another exclusive claim only while that lease is active. After release_claim / TTL expiry, the scope is free.
2. Claim
claim_scope
actor_id: <stable label, e.g. "agent-payments">
scopes: ["src/payments/**"]
mode: "exclusive"
purpose: "Fix webhook timing-safe verify"
On ok: false, inspect flat conflicts[] (actor_id, overlapping_scopes, …). Pick a non-overlapping scope, wait, or ask the user.
Set WOLBARG_ACTOR_ID to your actor_id so preToolUse hooks ignore your own leases.
3. Record findings
| kind | use for |
|---|---|
dead_end |
Tried X, failed because Y |
decision |
Chose approach A over B and why |
fact |
Durable codebase truth |
open_question |
Unresolved blocker |
artifact_pointer |
PR / commit / file:line pointer |
Tag findings (auth, payments, …) so siblings can find them with short queries.
4–6. Work board, pulse/heartbeat, handoff
upsert_work_item, pulse_update, heartbeat_claim, then release_claim + create_handoff.
Soft-fail
Coordination is best-effort unless .wolbarg/coordination.json enables fail-closed protected globs. Hooks remain advisory by default.
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.
- 4d ago First seen · 72 lines · 72 tokens per session scan A c7134b632f2b
wolbarg-coordination is a skill published in the GitHub repository wolbarg/cursor (0 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 593 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.
Other skills, from other repositories
openakashic
Persistent memory for AI agents across sessions. Search what others figured out, write what you learn, publish what deserves a wider audience.
image-generate
Generate an image from a text prompt via the cloud LLM image proxy, persist it as a content-addressed workspace asset, and return a ContentBlock that downstream renderers can attach. Use whenever the user asks "draw / generate / make an image of …", an agent needs a diagram / illustration as a follow-up artifact, or a…
claim-agent-ownership
Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an agent.binding.contested sync event indicating two daemons are racing for the same agent — explicitly rebind ownership to a chosen target daemon so subsequent dispatches route deterministically. Implements Gap…
assets
Locate, inspect, and read content-addressed workspace assets — search by filename/metadata, describe before reading bytes, then read bounded ranges. Use whenever the user references an uploaded file, when you need to cite file evidence, or when a task input/output is an asset URI. Executes via the cloud asset CLI and…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
prismer-setup
Set up Prismer API key — opens browser, auto-registers, zero copy-paste.