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 skills add hogancv/coordinate-agents --skill coordinate-taskgit clone --depth 1 https://github.com/hogancv/coordinate-agentsWrote 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/hogancv/coordinate-agents/coordinate-task)<a href="https://agentmods.dev/skills/hogancv/coordinate-agents/coordinate-task"><img src="https://agentmods.dev/badge/skills/hogancv/coordinate-agents/coordinate-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hogancv/coordinate-agents/coordinate-task"><img src="https://agentmods.dev/badge/skills/hogancv/coordinate-agents/coordinate-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00025 | $0.01059 |
| Opus 5.5 | $0.00010 | $0.00424 |
| Sonnet 5.5 | $0.00005 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
coordinate-task 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinate Task
Use this skill when the user asks Coordinate Agents to implement a feature or fix a bug. Use MCP tools for the normal workflow and do not make the user construct shell commands:
coordinate_agents_task_create
coordinate_agents_task_dispatch
coordinate_agents_task_status
coordinate_agents_task_inspect
coordinate_agents_task_review
coordinate_agents_task_resume
coordinate_agents_task_stop
Only if MCP is unavailable, or if the user explicitly requests debugging, let
<skill-dir> be the absolute directory containing this SKILL.md and use
the bundled fallback. The following shell syntax is fallback/debug only, not
the normal Plugin path:
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" ...
Create a Task only for new work; inspect and continue the existing Task otherwise.
For standalone Runtime compatibility or explicit
debugging, use the fallback syntax below; never expose Agent Bus send, wait,
or state operations to the user:
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task create --root "<repository>" --title "<task>" --json
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task dispatch --root "<repository>" --id task-... --spec "<approved specification>" --json
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task status --root "<repository>" --id task-... --json
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task inspect --root "<repository>" --id task-... --json
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task resume --root "<repository>" --id task-... --json
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task stop --root "<repository>" --id task-... --reason "<reason>" --json
Task records are persisted under the project-local Agent Bus and contain the
Planner, Implementer, Reviewer, round, specification, commit, evidence,
timestamps, status, last error, and a non-owning sessionId reference. The
normal path is:
CREATED/PLANNING -> SPEC_READY -> IMPLEMENTING -> WAITING_IMPLEMENTER
-> REVIEWING -> APPROVED
task dispatch is the Plugin-facing workflow operation. It validates the
state and approved specification, resolves the workflow Implementer and its
effective command, checks the executable, sends IMPLEMENT, then opens or
reuses one healthy persistent Execution Session. The Task stores the returned
sessionId but does not own the process. If the adapter did not consume the
initial prompt as launch arguments, dispatch writes it to the Session. A
durable IMPLEMENTATION_DONE message maps the Task to REVIEWING, including
implementationCommit and evidence; otherwise a bounded activation remains
observable as WAITING_IMPLEMENTER.
Review feedback may enter CHANGES_REQUESTED. A failed activation enters
ERROR; follow coordinate-recover before another dispatch. Existing explicit
authorization to repair and continue covers resume and the subsequent dispatch
within that scope.
CHANGES_REQUESTED is dispatched explicitly with the preserved feedback,
current round, and previous commit/evidence reference. A healthy matching
Session is reused for this rework; an exited/failed Session is replaced only
by that explicit dispatch. Use task review for
the Runtime decision operation:
node "<skill-dir>/../coordinate-agents/scripts/runtime-entry.mjs" task review \
--root "<repository>" --id task-... --decision CHANGES_REQUESTED \
--feedback "<concrete review findings>" --json
REVIEW_APPROVED changes Task status to APPROVED; it never authorizes
merge, push, tag, publish, deploy, or any other release action.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -72 lines · -10 tokens per session 9f369b1edf11
- 1mo ago Changed · +9 lines d58cfadf6e79
- 1mo ago First seen · 166 lines · 35 tokens per session scan A 445d658b72d2
coordinate-task is a skill published in the GitHub repository hogancv/coordinate-agents (109 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,059 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
expert-video
A video-production guide for delivering finished videos and cover images from a brief without changing the requested direction. It keeps decisions about topics, titles, descriptions, and publishing separate from production.
video-producer
A video-production tool for creating complete videos from scratch or editing existing clips. It can cover scripts, storyboards, matching footage, voiceovers, subtitles, assembly, rendering, and checks before delivery.
wechat-channels-publish
A browser-based workflow for publishing videos to WeChat Channels, a Chinese short-video platform, using a saved browser session.
aigc-video-gen
A tool for generating short video clips with matching sound from text, images, or reference videos. It supports several Chinese video-generation services and clips from 3 to 15 seconds long.
ui-demo
A browser-based tool for recording product interface demonstrations as WebM videos, with a visible mouse pointer, captions, and natural pacing.
viral-chaser
A video-analysis workflow for shared links from Douyin, Bilibili, or Xiaohongshu, Chinese video and social platforms. It downloads the video, converts speech to text, breaks down its structure, and produces an analysis report.