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 strikersam/autonomous-ai-agency --skill cowork-sessiongit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/cowork-session)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/cowork-session"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/cowork-session/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/strikersam/autonomous-ai-agency/cowork-session"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/cowork-session.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 | $0.00024 | $0.00448 |
| Opus 5 | $0.00012 | $0.00224 |
| Sonnet 5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
cowork-session 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 9d 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
Skill: cowork-session (Claude Cowork)
Purpose
Enables multiple developers to share an AI pair-programming session with context propagation, turn-taking, and collaborative state management.
When to Use
- Pair programming with an AI assistant as mediator
- Code review sessions with real-time context sharing
- Onboarding new team members (observe mode)
- Collaborative debugging sessions
Components
| Class | Role |
|---|---|
ContributorState |
Per-user state (role, cursor, activity) |
CollaborationContext |
Shared workspace context blob |
CoworkSession |
Turn-taking, role assignment, phase management |
SyncAgent |
Background sync with idle-editor eviction |
Session Roles
| Role | Permissions |
|---|---|
| HOST | Always can take editing control |
| PARTICIPANT | Can request edit; blocked if another editor is active |
| OBSERVER | Read-only; can only edit during IDLE/BRAINSTORMING |
Quick Start
from agents.cowork_session import CoworkSession, SessionRole
session = CoworkSession(session_id="s1", host_user_id="alice")
session.add_contributor("bob")
session.add_contributor("carol", role=SessionRole.OBSERVER)
session.request_edit("bob") # bob gets editing control
session.sync_context("bob", {"message": "Let's refactor this"})
Testing
pytest tests/test_cowork_session.py -v
12 tests covering CollaborationContext, CoworkSession, SyncAgent.
Branch
fix/quick-note-261-cowork
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.
- 9d ago First seen · 72 lines · 24 tokens per session scan A e64186512cb9
cowork-session is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 448 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
codebase-sync
Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
cog-onboarding
Personalize COG Second Brain workflow through role pack selection and vault initialization.
cog-weekly-reflection
Cross-domain pattern analysis with personal, professional, and project domain synthesis.