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.
git clone --depth 1 https://github.com/mertbarutcuoglu/agent-meshWrote 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/commands/mertbarutcuoglu/agent-mesh/mesh-watch)<a href="https://agentmods.dev/commands/mertbarutcuoglu/agent-mesh/mesh-watch"><img src="https://agentmods.dev/badge/commands/mertbarutcuoglu/agent-mesh/mesh-watch.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00095 |
| Opus 5 | $0.00004 | $0.00048 |
| Sonnet 5 | $0.00002 | $0.00019 |
| Haiku 4.5 | $0.00001 | $0.00010 |
Grade A, and why
mesh-watch 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 7d 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
Run mesh inbox --wait --responder-only using the Bash tool. This is a manual one-shot wait, separate from the plugin's persistent monitor: it waits for up to 55 seconds by default, emits at most one complete notification, and exits. If it returns an Agent Mesh query, answer it using the agent-mesh skill; run this command again to wait for another message.
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.
- 7d ago First seen · 6 lines · 8 tokens per session scan A 7eea925d5d79
mesh-watch is a command published in the GitHub repository mertbarutcuoglu/agent-mesh (4 stars, last pushed 28d ago), licensed MIT. It adds 8 tokens to every session and 95 once invoked, about $0.0000 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 commands, from other repositories
summon
Summon one skill into context for this session. Nothing is installed.
skill-heaven
Arm converge: auto-summon narrowly per capability gap (low|med).
skill-hell
Arm explore: auto-summon widely per capability gap (high|xhigh|max).
skill-ultra
Arm ultra: the top of the line, picks direction and depth per gap.
skill-zero
Zero cuts temporary skills by default; all cuts every skill summon.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.