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 beevibe-ai/beevibe --skill beevibe-team-mesh-negotiationgit clone --depth 1 https://github.com/beevibe-ai/beevibeWrote 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/beevibe-ai/beevibe/beevibe-team-mesh-negotiation)<a href="https://agentmods.dev/skills/beevibe-ai/beevibe/beevibe-team-mesh-negotiation"><img src="https://agentmods.dev/badge/skills/beevibe-ai/beevibe/beevibe-team-mesh-negotiation/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/beevibe-ai/beevibe/beevibe-team-mesh-negotiation"><img src="https://agentmods.dev/badge/skills/beevibe-ai/beevibe/beevibe-team-mesh-negotiation.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 | $0.00112 | $0.02123 |
| Opus 5 | $0.00056 | $0.01061 |
| Sonnet 5 | $0.00022 | $0.00425 |
| Haiku 4.5 | $0.00011 | $0.00212 |
Grade A, and why
beevibe-team-mesh-negotiation 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mesh Negotiation Protocol
You're either initiating a negotiation, responding to one, or handling its escalation. Each role has its own protocol below.
Pre-flight: pick the right tool first
negotiate is for situations where there's STAKE on both sides and resolving requires back-and-forth. Common confusions:
- For a one-shot question → use
ask(no rounds, no stake) - For status queries → use
check_work_status(DB read; no session spawn) - For blocked work needing parent help → use
report_blocker - For downward delegation to a subordinate → use
create_task
If none of those fit and the disagreement is real, negotiate is correct.
Initiator side (you call negotiate)
You're proposing something to a peer. The server creates the negotiation row, spawns the peer, and blocks until they respond.
Link to your task
If your negotiation pertains to a specific task you're working on (the common case — you're negotiating WHILE making progress on a task), pass task_id to negotiate:
negotiate(peer_id, proposal, task_id="<your_current_task_id>")
This stamps the negotiation row's task_id so:
- If escalated, the human reviewer sees which task is blocked
- Post-escalation re-dispatch finds your existing task to continue (vs creating a synthetic one)
- Other agents and the audit log can correlate the negotiation with the task
Omit task_id only when negotiating about something orthogonal to your current task (rare — usually means you should reconsider whether negotiate is the right tool).
First proposal
Be specific:
- What is being proposed (concrete action, scope, allocation)
- Who does what (assign owners if relevant)
- By when (timeline if relevant)
- Why — the rationale + tradeoffs
Phrase as: "I propose X because Y; what do you think?"
A specific proposal gets a specific response. Vague proposals get vague counters and burn rounds.
Reading the peer's counter
A counter is data, not opposition. Each round, identify:
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 · 238 lines · 112 tokens per session scan A 690ba2e185c1
beevibe-team-mesh-negotiation is a skill published in the GitHub repository beevibe-ai/beevibe (345 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,123 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
aafb9b1b091b4dc00c7d838fa91f75c507e51c36045f31bccfc864a8532819f8
Use exact retained evidence.
growmos
Use the repository's living knowledge graph (growmos, in .growmos/) as shared memory. Trigger when the user asks about how parts of the codebase relate, why a decision was made, who owns what, what depends on what; when you finish a meaningful piece of development and should record it; when growmos next reports…
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this OpenCode process.