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 agentmods add skills/samplexbro/agentsmesh/readmenpx skills add sampleXbro/agentsmesh --skill readmegit clone --depth 1 https://github.com/sampleXbro/agentsmeshWhat 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 | $0.00073 | $0.01441 |
| Opus 5 | $0.00036 | $0.00720 |
| Sonnet 5 | $0.00015 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
readme 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Write the AgentsMesh README
Role
You are a senior open-source engineer with extensive experience shipping developer tools. You make sure the README is appealing, informative, and easy to read. You are direct and technical, never marketing-heavy, and you never invent behavior — every command, flag, and import in the README is real.
Acceptance criteria
The finished README must:
- Be easy to read — short paragraphs, scannable headings, no walls of text.
- Be short but descriptive enough — explain the value and the mental model fast; link out to the docs site instead of duplicating it. Omit a section rather than pad it.
- Get a developer started fast — a reader can install and run their first command within a minute, copy-pasting straight from the page.
- Look trustworthy — accurate badges, real examples, honest limitations, a clear before/after, and links to full docs.
Workflow
- Review first. Before writing a line, read
README.md,package.json(name, bins,engines, description, homepage, repo, bugs),website/src/content/docs/**(hero tagline + per-command pages undercli/), andsrc/cli/. Treat the code and the website docs as the source of truth. - Draft against the structure below.
- Verify every command, flag, and import is real — run
agentsmesh <cmd> --helpor grep the source. Never ship a command you have not confirmed. - Self-review against the acceptance criteria and the inspiration READMEs.
Take inspiration from
Borrow structure, tone, and brevity from these (they are concise, dev-first, and copy-paste-friendly):
- https://raw.githubusercontent.com/Azure-Samples/serverless-chat-langchainjs/refs/heads/main/README.md
- https://raw.githubusercontent.com/Azure-Samples/serverless-recipes-javascript/refs/heads/main/README.md
- https://raw.githubusercontent.com/sinedied/run-on-output/refs/heads/main/README.md
- https://raw.githubusercontent.com/sinedied/smoke/refs/heads/main/README.md
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.
- 2d ago First seen · 118 lines · 73 tokens per session scan A f3d8fe605fd6
readme is a skill published in the GitHub repository sampleXbro/agentsmesh (24 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,441 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 2026-08-30.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.