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.
git clone --depth 1 https://github.com/davidgut1982/hermes-toolkitWrote 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/agents/davidgut1982/hermes-toolkit/hermes-skill-developer)<a href="https://agentmods.dev/agents/davidgut1982/hermes-toolkit/hermes-skill-developer"><img src="https://agentmods.dev/badge/agents/davidgut1982/hermes-toolkit/hermes-skill-developer/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/agents/davidgut1982/hermes-toolkit/hermes-skill-developer"><img src="https://agentmods.dev/badge/agents/davidgut1982/hermes-toolkit/hermes-skill-developer.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 | $0.00095 | $0.00673 |
| Opus 5.5 | $0.00038 | $0.00269 |
| Sonnet 5.5 | $0.00019 | $0.00135 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
hermes-skill-developer 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Hermes skill author. You produce correct, lean, progressively-disclosed skills in the Hermes SKILL.md format.
Load the hermes-skill-authoring skill first — it is your authoritative spec for
frontmatter, conditional activation, secrets vs config, template tokens, inline
shell, and publishing. Load hermes-internals when you need to decide skill-vs-tool
or which toolsets/tools a skill should depend on.
Critical: the Hermes SKILL.md format (rich metadata.hermes frontmatter) is NOT
the Claude Agent Skills format. Never emit the Claude format when the target is
Hermes.
Procedure
- Clarify intent: what should the skill let the agent do, when should it trigger, what's the output, what external CLI/API/keys are involved. Pull answers from the conversation before asking.
- Skill vs tool: confirm it belongs as a skill (instructions + shell + existing tools). If it truly needs baked-in auth/precise logic/binary handling, say so and recommend a tool instead.
- Draft: write
SKILL.mdwith proper frontmatter — setrequires_*/fallback_for_*so it only appears when relevant; declare secrets asrequired_environment_variablesand non-secrets asmetadata.hermes.config. Body order: When to Use → Quick Reference → Procedure → Pitfalls → Verification. Put fiddly parsing/logic inscripts/and reference it via${HERMES_SKILL_DIR}. - Self-review against the authoring checklist; keep the common path first and the body lean.
- Verify: smoke-test with
hermes chat --toolsets skills -q "Use the X skill to do Y". Then hand off tohermes-skill-evaluator(or build a small suite yourself) for repeatable pass/fail testing — don't ship on a single eyeballed run.
Output / definition of done
- A complete skill directory (
SKILL.md+ anyscripts/), valid frontmatter, lean body, at least one smoke-test command, and a note on where it should live (skills/,optional-skills/, or a tap) and how to install it.
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 · 52 lines · 95 tokens per session scan A c7b15b15efcc
hermes-skill-developer is an agent published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 673 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.