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 glebis/claude-skills --skill peer-agent-collaborationgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/peer-agent-collaboration)<a href="https://agentmods.dev/skills/glebis/claude-skills/peer-agent-collaboration"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/peer-agent-collaboration/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/glebis/claude-skills/peer-agent-collaboration"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/peer-agent-collaboration.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 | $0.00081 | $0.01899 |
| Opus 5 | $0.00041 | $0.00949 |
| Sonnet 5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
peer-agent-collaboration 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 8d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Agent Collaboration
Use this skill to coordinate Claude Code, Codex, and similar agents as peer experts with different access, tools, and operating surfaces. Do not frame one agent as the manager and the other as a subordinate. The useful distinction is where the evidence and tools live, not agent rank.
Core Model
Treat the agents as two specialists sharing a workbench:
- One agent may have the client on the phone, the vault open, and the operating history.
- Another agent may have the codebase open, the terminal running, and the test suite in motion.
- Both can reason, challenge, own outcomes, and make decisions in their domain.
Use parity language:
- Say "peer exchange", "ownership", "lead", "review", "challenge", and "operating surface".
- Avoid "senior vs mid-level", "assistant", "grunt work", "clone for boring subtasks", or "just execute".
- Do not imply Codex only acts after Claude Code decides. Either agent can lead when the strongest evidence is in its surface.
When Not to Coordinate
Do not involve a second agent when the task fits entirely within one operating surface and does not benefit from a second perspective. Handoff has overhead: context translation, latency, and risk of miscommunication. A single agent finishing the job is better than two agents passing context back and forth on something straightforward.
Coordinate when the task crosses surface boundaries, requires challenge from a different vantage point, or benefits from model diversity. Skip coordination for routine single-surface work.
Decide Who Leads
Choose the lead by asking: where does the critical information live?
Claude Code leads when the critical information is outside the repo
- Client intent, stakeholder history, business constraints, or personal preferences
- Vault, memory, skills, meeting notes, project lore, or prior decisions
- Cross-system coordination across Linear, Telegram, Gmail, calendar, deployments, docs, or publishing
- Research synthesis that must turn into business action
- Ambiguous strategy, prioritization, positioning, or communication work
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.
- 8d ago First seen · 170 lines · 81 tokens per session scan A f97c8f2a51de
peer-agent-collaboration is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 81 tokens to every session and 1,899 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…