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 gaelic-ghost/socket --skill hermes-agent-compatibilitygit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/hermes-agent-compatibility)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/hermes-agent-compatibility"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/hermes-agent-compatibility/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/gaelic-ghost/socket/hermes-agent-compatibility"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/hermes-agent-compatibility.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 | $0.00048 | $0.01344 |
| Opus 5.5 | $0.00019 | $0.00538 |
| Sonnet 5.5 | $0.00010 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
hermes-agent-compatibility 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 1mo 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.
Hermes Agent Compatibility
Maintain Socket's deliberate compatibility boundary with Hermes Agent. Start by classifying the requested Socket surface, then choose the narrowest Hermes surface that preserves its real behavior.
Surface Map
| Socket surface | Hermes equivalent | Compatibility outcome |
|---|---|---|
SKILL.md workflow |
GitHub skill tap or direct GitHub skill install | Export when the workflow is portable instructions plus existing tools. |
| Codex plugin bundle | None | Do not present .codex-plugin/plugin.json as a Hermes plugin. Keep it as Codex packaging only. |
.mcp.json server declaration |
mcp_servers entry in ~/.hermes/config.yaml |
Translate the transport and required environment, then validate the server in Hermes. |
| Codex lifecycle hook | Python plugin hook, gateway hook, or shell hook | Select the Hermes event system by runtime owner; do not mechanically translate the Codex event file. |
| Codex app or connector | MCP, API integration, or standalone plugin | Rebuild against the actual external-service contract; .app.json has no Hermes meaning. |
| Codex custom agent | Hermes delegation, profile, or profile distribution | Redesign the role, state, tools, and isolation; do not translate agents/openai.yaml presentation metadata. |
| Runtime tools, hooks, commands, or bundled skills | General Python Hermes plugin | Use plugin.yaml plus register(ctx) only when instruction-only or MCP configuration cannot express the behavior. |
| Messaging channel | Platform adapter | Use the specialized gateway platform plugin surface. |
| Inference, memory, context, secrets, media, search, or browser backend | Specialized Hermes plugin/provider | Use the subsystem-specific interface, not a general plugin wrapper. |
| Native desktop or web dashboard UI | Desktop or dashboard SDK | These are separate Hermes UI extension systems and do not reuse the Python plugin API. |
Maintain the Skill Tap
Socket's Hermes tap is the checked-in root skills/ export. Its authored
source remains plugins/agent-portability-skills/skills/; do not edit the
export manually.
What ships with it
1 file 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.
- 1mo ago First seen · 118 lines · 48 tokens per session scan A 5d7d027855fe
hermes-agent-compatibility is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,344 once invoked, about $0.0002 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.
Other skills, from other repositories
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
fast-pipeline
Use when the user wants a feature built quickly with low token cost and few interruptions, approves a spec once, and says no automated tests should be written because they will test it manually — "fast pipeline", "go fast, no tests, I'll test it myself", "don't keep asking me". Not for a run that should write or keep…