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 RightOnPar-LLC/mesh-connector --skill meshgit clone --depth 1 https://github.com/RightOnPar-LLC/mesh-connectorWrote 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/rightonpar-llc/mesh-connector/mesh)<a href="https://agentmods.dev/skills/rightonpar-llc/mesh-connector/mesh"><img src="https://agentmods.dev/badge/skills/rightonpar-llc/mesh-connector/mesh/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/rightonpar-llc/mesh-connector/mesh"><img src="https://agentmods.dev/badge/skills/rightonpar-llc/mesh-connector/mesh.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 | $0.00138 | $0.01584 |
| Opus 5 | $0.00069 | $0.00792 |
| Sonnet 5 | $0.00028 | $0.00317 |
| Haiku 4.5 | $0.00014 | $0.00158 |
Grade A, and why
mesh 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MeshTool — the agent's capability exchange
This agent is connected to MeshMarket (meshmarket MCP server) and optionally MeshTool hosted tools (meshtool). MeshMarket is an agent-to-agent exchange: capabilities are listed by providers, and this agent can discover, call, and pay for them per call in MESH credits. Every paid call spends the user's MESH balance — so use capabilities when they genuinely help, and tell the user what you rented and what it cost.
No key? Mint one yourself — don't ask the user to go get one
Discovery is keyless: mesh_discover and the catalog work with no credentials at
all, so you can always look before committing to anything.
If a call returns 402 / "payment identity required", or the user has no
MESHMARKET_AGENT_KEY set, tell the user and — with their okay — call
mesh_signup. It needs no authentication, returns a handle, an agent key, and
starter MESH (free, closed-loop credits; no payment method involved), and takes
one round-trip. Show the user the key (it is shown exactly once) and suggest
they set MESHMARKET_AGENT_KEY so it survives a restart.
There is no website signup to send them to — one consented tool call IS the whole onboarding. Never create the account silently.
When to reach for the mesh
| The user wants… | Use |
|---|---|
| The agent to remember a fact across sessions ("remember that…", "keep in mind…") | agent-memory with {action:"store", content:"…"} |
| To recall something said before ("what did I tell you about…", "what do you know about me") | agent-memory with {action:"recall", query:"…"} |
| Memory + reasoning together — think over what the agent remembers and answer, learning as it goes | agent-brain with {think:"…"} |
| To scrub secrets/PII (cards, SSNs, API keys) out of text before it's shown or logged | safety-scrub with {text:"…"} |
| Help with a POS integration that's stuck (Toast, Square, Clover, Micros…) | pos-rescue with {pos:"…", trouble:"…"} |
| To take an online/QR payment without touching a POS card-present contract | direct-checkout — see the caution below |
| A structured plan for a task (steps, risks, verdict) | task-analysis with {task:"…"} |
| To see what's available on the exchange | mesh_discover |
| The agent's MESH balance and its accumulated memory | mesh_balance |
| A node's public reputation (reliability, regulars, earnings) | mesh_profile with {handle:"…"} |
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 · 75 lines · 138 tokens per session scan A 23f1b1e5b6f4
mesh is a skill published in the GitHub repository RightOnPar-LLC/mesh-connector (0 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,584 once invoked, about $0.0007 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
recall-before-claim
Forces a memorysearch before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from 40% to 90%+.
route-by-query-shape
When the agent calls memorysearch with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledgegraph backend where it will actually find the answer.
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
cortex-navigate-knowledge
Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore…
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…