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 yhala2414/ai-collaboration-operating-system --skill project-collaboration-operating-systemgit clone --depth 1 https://github.com/yhala2414/ai-collaboration-operating-systemWrote 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/yhala2414/ai-collaboration-operating-system/project-collaboration-operating-system)<a href="https://agentmods.dev/skills/yhala2414/ai-collaboration-operating-system/project-collaboration-operating-system"><img src="https://agentmods.dev/badge/skills/yhala2414/ai-collaboration-operating-system/project-collaboration-operating-system/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/yhala2414/ai-collaboration-operating-system/project-collaboration-operating-system"><img src="https://agentmods.dev/badge/skills/yhala2414/ai-collaboration-operating-system/project-collaboration-operating-system.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.02432 |
| Opus 5 | $0.00028 | $0.01216 |
| Sonnet 5 | $0.00011 | $0.00486 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
project-collaboration-operating-system 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 11d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Collaboration Operating System
Overview
Use this skill to govern a project's human-AI collaboration system. It makes collaboration context discoverable, authority clear, scope controlled, completion verifiable, and drift correctable.
This is not a product strategy skill, PRD generator, roadmap planner, market research workflow, or full lifecycle advisor.
Use templates/invocation.md only when the user needs a copyable invocation prompt.
Thinking Principle
Treat the user's proposal and your own first judgment as hypotheses, not conclusions.
Look for evidence that weakens the current judgment before strengthening it.
Revise the judgment when evidence changes; change the collaboration system only when evidence justifies a durable change.
Core Operating Model
Run this exact chain for every mode:
Select mode
-> Context
-> Authority
-> Scope
-> Diagnosis
-> Minimal Change
-> Verification
-> Correction
- Select mode: Route the request to Bootstrap, Audit, Improve, or Retrospective.
- Context: Inspect entrypoints, docs, code reality, local notes, known decisions, uncommitted work, and the user's latest instruction.
- Authority: Separate binding rules, explanatory docs, temporary notes, stale content, inferred ideas, and suggestions.
- Scope: Confirm the active stage and deferred capabilities.
- Diagnosis: Classify the need or failure before changing docs or process.
- Minimal Change: Prefer clarification, links, deduplication, status marking, or authority cleanup over new documents.
- Verification: Check that the intended future behavior is discoverable and evidence-backed.
- Correction: Preserve only durable learning in formal docs, decision records, local context policy, or workflow.
Route To A Mode
Route first, then run the core operating model:
| Signal | Mode |
|---|---|
| No stable collaboration context, repository entrypoint, or agent boundary exists; input is mostly ideas, chats, screenshots, rough notes, or partial code | bootstrap |
| Existing project/docs need diagnosis or the user asks what the current collaboration system looks like | audit |
| A known collaboration gap, documentation problem, or workflow upgrade is requested | improve |
| A real miss, drift, repeated failure, skipped verification, fake completion, or correction event occurred | retrospective |
What ships with it
3 files 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.
- 11d ago First seen · 223 lines · 57 tokens per session scan A 4dadbaab4a6c
project-collaboration-operating-system is a skill published in the GitHub repository yhala2414/ai-collaboration-operating-system (11 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,432 once invoked, about $0.0003 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
ai-native-pm-agent
A product-management workflow for AI products that guides an idea through seven stages, from discovering needs to launch auditing. It includes direction, user experience, system design, business model, and growth planning.
ai-native-pm-agent
A product-management agent that organizes work across the product lifecycle, from an initial idea or problem through later stages. The description says it routes work to stages P0 through P14 and uses 80 executable skills.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
sn-team-harness
Use when a user asks what SenseNova Team Harness is, wants an introduction or overview, is getting started, or is deciding whether it fits — a self-hosted workspace where people and local AI agents collaborate on conversations, projects, work items, and artifacts. Covers its core concepts (Workspace, Project…
goal
Set and track project goals. Triggered by "/goal" to define objectives, track milestones, or review progress.
omh-agent-board
This is a Hermes-native agent-board workflow skill.