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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill cli-hermesgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-hermes)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-hermes"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-hermes/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-hermes"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/cli-hermes.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 | $0.00027 | $0.05916 |
| Opus 5.5 | $0.00011 | $0.02366 |
| Sonnet 5.5 | $0.00005 | $0.01183 |
| Haiku 4.5 | $0.00003 | $0.00592 |
Grade C, and why
cli-hermes scanned grade C with 2 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **`--yolo` lifts only the dangerous-action gate.** Observed live 2026-09-14: without `--yolo` a headless chat wrote an ordinary scratch file (exit 0), while `rm -rf <scratch dir>` came back `BLOCKED: Command flagged as Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
ancestry = subprocess.check_output(['ps', '-o', 'command=', '-p', str(os.getppid())]).decode() How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical source:
.skilled/skills/cli-external-orchestration/cli-hermes/. This is a generated markdown-only copy so Hermes can load the skill without scanning the canonical directory. Readreferences/,assets/andscripts/from the canonical path above.
Hermes Agent CLI Orchestrator - Cross-AI Task Delegation
CRITICAL — SELF-INVOCATION PROHIBITED
This skill dispatches to the Hermes Agent binary (
hermes). If the agent currently reading this skill is itself running inside Hermes (detection signals in §2), the skill MUST refuse to load and return the documented error instead of generating anyhermesinvocation. Hermes has in-process delegation of its own (delegate_task), so a Hermes session hands work out through that, never by re-dispatching this CLI.
Orchestrate Hermes Agent (Nous Research's open-source, Python-based agent CLI) for quiet oneshot coding dispatch, cross-AI validation, and model routing through the operator's LLM Gateway provider. The evidence base is the phase 001 research synthesis and, once recorded, the live contract pin: research synthesis, contract pin. Claims marked source-read, unconfirmed come from the installed Hermes source (v0.21.1) and await the pin.
Core principle: use Hermes for what its surface offers, delegate research and review lineages to the shared deep-loop runtime, validate the returned output, and keep the calling AI as conductor.
1. WHEN TO USE
Activation Triggers
- Headless Hermes dispatch: the task explicitly names Hermes, Nous Research, or the Hermes agent.
- Cross-AI validation: an independent implementation attempt, review, or second opinion through a Hermes-hosted model.
- LLM Gateway roster dispatch: a task that wants
deepseek-v4.1-flashorglm-5.3-flashthrough Hermes's tool loop rather than Pi's or OpenCode's. - Project skills and plugins: a task that concerns Hermes's repo-local
.hermes/skills,.hermes/plugins, or its skill and plugin commands. - Deep-loop fan-out: a
/deep:researchor/deep:reviewlineage on--executor=cli-hermes.
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.
- today Changed a18c1aa3a063
- 5d ago Changed · -6 tokens per session 3acd1f18a071
- 16d ago Changed · -33 lines bf30a564f6c1
- 19d ago Changed 525c19e864f1
- 22d ago Changed cce6591e1fdc
- 23d ago Changed fb1c489d2421
- 28d ago Changed 3d609281ea76
- 1mo ago First seen · 352 lines · 33 tokens per session scan C 5cd7d764e12b
cli-hermes is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (37 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 5,916 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…