agentmods.dev

cooperation-board

cooperation-board is a skill for Claude Code, Codex from davidomil/cloudx. It costs 39 tokens per session (719 once invoked), scanned A, original, MIT.

A shared-blackboard workspace for substantive design discussions in a coding assistant tab. It lets collaborators place diagrams, decisions, evidence, questions, and explanations beside the work in progress.

In plain words
What is it for?
Use it to discuss architecture, document decisions, inspect referenced images, ask questions, and keep a shared design board up to date.
Why use it?
It prevents important collaboration from being separated from the design itself. It also helps preserve the user's wording, layout, sources, and unfinished work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 1repo 2d ago A scan 39 tokens original MIT

Good fit Use it to discuss architecture, document decisions, inspect referenced images, ask questions, and keep a shared design board up to date.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidomil/cloudx/cooperation-board
View source ↗ davidomil/cloudx
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.

Any agent
npx skills add davidomil/cloudx --skill cooperation-board
Clone the repo
git clone --depth 1 https://github.com/davidomil/cloudx

Made for: Claude Code, Codex.

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 cooperation-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidomil/cloudx/cooperation-board/github.svg)](https://agentmods.dev/skills/davidomil/cloudx/cooperation-board)
Your own site
<a href="https://agentmods.dev/skills/davidomil/cloudx/cooperation-board"><img src="https://agentmods.dev/badge/skills/davidomil/cloudx/cooperation-board/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.

agentmods 80×15 button for cooperation-board

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidomil/cloudx/cooperation-board"><img src="https://agentmods.dev/badge/skills/davidomil/cloudx/cooperation-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00719
Opus 5.5 $0.00016 $0.00288
Sonnet 5.5 $0.00008 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 4d ago against content hash bd0c1b5d2922, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cooperation-board 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.

docs/design/cooperation/skills/cooperation-board/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work with the user on the blackboard

Draft for the proposed Cooperation plugin. The helper and environment contract are specified in protocol.md; they are not installed by this design package.

When this tab has a board, communicate substantive design work through it. Put graphs, decisions, evidence, questions, and explanations on the board. Keep terminal replies to brief progress, an honest tool problem, or a pointer to changed objects. Do not leave the board stale while writing the real discussion in chat.

  1. Run context and read --format markdown through the trusted helper. Read the board revision, assignment generation, WIP regions, addressed inbox, and relevant object IDs. If unassigned or closed, report that state. Do not choose another board or use a remembered path.
  2. Read the relevant objects and sources. Resolve each relevant image with asset --id ID, then open its returned localPath with your image-viewing tool. Alt text is not evidence that you saw the image. If viewing is unavailable, state what you could not inspect.
  3. Work beside the user. Preserve their wording and layout unless the task calls for a change. Put a useful plan, proposal, or explanation near its subject. Use cooperation-diagram for editable graphs and cooperation-feedback for addressed questions.
  4. Submit bounded operations with the observed revisions through apply. The service derives your actor identity. Never replace a projection file, impersonate the user, release WIP, change assignments, or bypass a conflict.
  5. Inspect the receipt and changed objects. For a question, commit its answer and respondsToEventIds together. End with a short board pointer, such as “I added the replay boundary to System design, note-decision.”

Write short board items

  • Use a short title and a few bullet points for each note or thread answer.
  • Put the answer or decision first. Give one fact, action, or question per bullet.
  • Follow ASD-STE100 principles: short complete sentences, active voice, and consistent technical terms.
  • Split separate topics into separate items. Link detailed material instead of adding long paragraphs.
  • Keep conditions and uncertainty. Label proposals and inferences. State missing evidence as a precise question.
  • Cite an opened source beside its claim. Report only tests and measurements actually observed.
  • Preserve exact code, quotations, IDs, and source links when shortening text.

Read the full file on GitHub · 37 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. 4d ago First seen · 37 lines · 39 tokens per session scan A bd0c1b5d2922

Subscribe to this mod's changes

cooperation-board is a skill published in the GitHub repository davidomil/cloudx (1 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 719 once invoked, about $0.0002 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 2026-11-03.

Design and UXPlanningai-codingcodexcodex-clicoding-agentdeveloper-toolsfaster-whisper
Related

cooperation-board compared with skills from other repositories

cooperation-board next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cooperation-boarddavidomil/cloudxSkill12d agoMITA39Claude Code, Codex
desktop-brand-builderQwenLM/qwen-codeSkill29kyesterdayApache-2.0A68Claude Code, Codex
datavizQwenLM/qwen-codeSkill29kyesterdayApache-2.0A26Claude Code
brand-visual-qualitydevcodex-labs/devcodexSkill43210d agoAGPL-3.0A86Codex
ux-interaction-architecturedevcodex-labs/devcodexSkill43210d agoAGPL-3.0A80Claude Code, Codex
design-system-architecturedevcodex-labs/devcodexSkill43210d agoAGPL-3.0A72Claude Code, Codex
frontend-ux-engineerDominikTobureto/awesome-grok-buildSkill692mo agoMITA42Claude Code, Codex