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 insodimension/awesome-agent-protocols --skill agent-protocolsgit clone --depth 1 https://github.com/insodimension/awesome-agent-protocolsWrote 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/insodimension/awesome-agent-protocols/agent-protocols)<a href="https://agentmods.dev/skills/insodimension/awesome-agent-protocols/agent-protocols"><img src="https://agentmods.dev/badge/skills/insodimension/awesome-agent-protocols/agent-protocols/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/insodimension/awesome-agent-protocols/agent-protocols"><img src="https://agentmods.dev/badge/skills/insodimension/awesome-agent-protocols/agent-protocols.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 | $0.00163 | $0.03244 |
| Opus 5.5 | $0.00065 | $0.01298 |
| Sonnet 5.5 | $0.00033 | $0.00649 |
| Haiku 4.5 | $0.00016 | $0.00324 |
Grade A, and why
agent-protocols 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 2mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Protocols
Guides agent/harness engineering toward using, extending, and contributing to established AI agent protocol standards rather than inventing ad-hoc solutions.
Knowledge base: This skill lives inside the awesome-agent-protocols repo, which catalogs 53+ protocols across 11 stack layers. The catalog is the source of truth; this skill makes it actionable during development.
This skill is self-improving. Every run must end with a gotcha review (see Self-Improvement Protocol).
This skill is a checklist, not a suggestion. Every mode below is a numbered checklist. You MUST tick each
[ ]by writing its status + exit-criterion outcome in your response BEFORE moving to the next step. Skipping a step without documenting why is a skill violation.
Pre-flight — ALWAYS (before any mode)
- PF-1. Read references/gotchas.md. Exit: you can state the 3 most recent dated entries in one sentence each (or confirm the log is empty).
- PF-2. Read the protocol catalog. Read the repo's
README.md(two levels up from this skill) to load the current protocol taxonomy. Exit: you can name the 11 stack layers. - PF-3. Read the decision tree. Read references/decision-tree.md. Exit: you can map the 10 primary "you're building..." rows to their protocols.
- PF-4. Understand the user's context. What are they building? What layer of the stack? What's the integration target? Exit: one sentence stating the task and its stack layer.
- PF-5. Pick the mode. Exit: one of Recommend / Lookup / Audit / Contribute written down.
Modes
| Mode | When to use | Output |
|---|---|---|
| Recommend | User is building something and needs to know which protocol(s) apply | Protocol recommendation with rationale + wire examples |
| Lookup | User wants spec details, wire messages, or examples for a specific protocol | Spec summary + verbatim wire examples from examples/ |
| Audit | User has existing code and wants to check protocol compliance or find protocol opportunities | Compliance report + specific recommendations |
| Contribute | User built something protocol-adjacent and wants to contribute back | Contribution path: which spec, which repo, what format |
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.
- 2mo ago First seen · 193 lines · 163 tokens per session scan A 849055cf73f5
agent-protocols is a skill published in the GitHub repository insodimension/awesome-agent-protocols (10 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 163 tokens to every session and 3,244 once invoked, about $0.0007 per session on Opus 5.5. 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.
agent-protocols compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-protocolsinsodimension/awesome-agent-protocols | Skill | 10 | 1mo ago | CC0-1.0 | A | 163 | Claude Code, Codex |
| design-taste-frontendarchestra-ai/archestra | Skill | 4.4k | today | none | A | 107 | Claude Code, Codex |
| ts-modernOrcaQubits/agentic-commerce-skills-plugins | Skill | 40 | 2d ago | MIT | A | 47 | Claude Code |
| nlweb-auth-multitenancyOrcaQubits/agentic-commerce-skills-plugins | Skill | 40 | 2d ago | MIT | A | 83 | Claude Code |
| nlweb-dev-patternsOrcaQubits/agentic-commerce-skills-plugins | Skill | 40 | 2d ago | MIT | A | 0 | Claude Code |
| nlweb-mcp-serverOrcaQubits/agentic-commerce-skills-plugins | Skill | 40 | 2d ago | MIT | A | 89 | Claude Code |
| nlweb-retrieval-backendsOrcaQubits/agentic-commerce-skills-plugins | Skill | 40 | 2d ago | MIT | A | 120 | Claude Code |