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 HybridAIOne/hybridclaw --skill hermes3000-writinggit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/hermes3000-writing)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/hermes3000-writing"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hermes3000-writing/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/hybridaione/hybridclaw/hermes3000-writing"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/hermes3000-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 138 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.02646 |
| Opus 5 | $0.00039 | $0.01323 |
| Sonnet 5 | $0.00016 | $0.00529 |
| Haiku 4.5 | $0.00008 | $0.00265 |
Grade A, and why
hermes3000-writing scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Never call Hermes3000 with `curl` or a raw `Authorization: Bearer ...` header. How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes3000 Writing
Overview
Use Hermes3000 when the user wants a durable long-form writing project managed in the writing portal, not just a one-off draft in chat. Hermes3000 stores book structure, chapter content, consistency memory, timeline data, stats, and exports.
For endpoint details, request shapes, and examples, read
references/api-workflow.md before making live API calls.
Secret Refs
The bundled helper sends all live Hermes3000 calls through the HybridClaw
gateway proxy, matching the Salesforce skill pattern. Login credentials are
sent as <secret:NAME> placeholders; the gateway resolves them server-side,
captures the returned Hermes3000 JWT into HERMES3000_JWT, and returns only a
capture confirmation. The JWT does not enter the agent context.
Never call Hermes3000 with curl or a raw Authorization: Bearer ... header.
Use node skills/hermes3000-writing/scripts/hermes3000.cjs ... run ... for
live calls so the gateway injects and captures secrets server-side.
Run these helper commands exactly as documented. Do not add Node permission
flags such as --experimental-permission, and do not rewrite skills/...
paths to /workspace/skills/...; the helper needs runtime-provided gateway
access for secret resolution.
Cloud and chat/TUI users may not have a terminal. Only ask the user to set
secrets with chat/TUI secret commands; do not ask them to run node, curl, or
hybridclaw shell commands. If HERMES3000_JWT is missing or blocked, run
auth.login yourself through the helper. The helper does not prompt for email
or password; it resolves HERMES3000_EMAIL and HERMES3000_PASSWORD from the
gateway secret store.
Ask the user to set the login inputs once through browser admin first:
- Browser admin: open the active HybridClaw admin URL ending in
/admin/secretsand setHERMES3000_EMAILandHERMES3000_PASSWORD. - Browser
/chator TUI fallback:
/secret set HERMES3000_EMAIL [email protected]
/secret set HERMES3000_PASSWORD <password>
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.
- 13d ago First seen · 259 lines · 78 tokens per session scan A 9a4d3794551a
hermes3000-writing is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 2,646 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.