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 AtlasOmnia/hermes-custom-pack --skill external-model-reviewgit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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/atlasomnia/hermes-custom-pack/external-model-review)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/external-model-review"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/external-model-review/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/atlasomnia/hermes-custom-pack/external-model-review"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/external-model-review.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 | $0.00042 | $0.01566 |
| Opus 5 | $0.00021 | $0.00783 |
| Sonnet 5 | $0.00008 | $0.00313 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
external-model-review 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 10d 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.
This is a copy
100% identical to external-model-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Model Review
When to use
Use this skill when the user asks a named external model or provider to:
- critique an implementation plan, architecture, specification, major article, README, or release candidate;
- pressure-test a consequential decision;
- provide an independent spec/security/quality pass;
- review something through OpenRouter, Claude, Gemini, Fable, or another specific model;
- revise the original artifact after the critic pass.
This is a review workflow, not general brainstorming. Load multi-model-brainstorming instead when the goal is divergent idea generation across several models.
Core rule
The external model is an independent critic, not an authority. Preserve its exact output, then verify every material finding against the source artifact, repository, and authoritative platform documentation before changing anything.
Workflow
1. Establish the review target
- Read the complete canonical artifact.
- Capture the relevant source/repository evidence and constraints.
- State whether the request is critique-only or critique-plus-amendment. If the user says “revise,” amend the canonical artifact after verification while preserving the original in the review artifacts.
2. Discover and pin the model
- Query the provider’s live model catalog for the exact current ID.
- Prefer a pinned model/version over a moving
latestalias when reproducibility matters. - Never infer availability or version from memory.
- Preflight credentials without printing them.
3. Build a rigorous critic prompt
Require:
- a decisive verdict;
- blocking findings with severity;
- concrete corrections and closure tests;
- architecture/trust-boundary analysis;
- migration, compatibility, rollback, performance, accessibility, privacy, and live-acceptance review where relevant;
- explicit separation of facts evident from the supplied material versus model judgment;
- no claims that files were saved or external actions occurred.
4. Preserve provenance
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.
- 10d ago First seen · 156 lines · 42 tokens per session scan A d4e090f6ac06
external-model-review is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 25d ago), licensed MIT. It adds 42 tokens to every session and 1,566 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to external-model-review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
config
Use when configuring obshare-cli credentials, checking saved settings, testing connectivity, clearing local config, or setting optional Obsidian bridge values used by the V0.2.0 direct-share stack.
obshare-cli
Use when setting up obshare-cli 0.2.0, reviewing available commands, or choosing the right command for config, upload, permission, history, delete, and the plugin-first direct-share workflow.
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
upload
Use when uploading a Markdown note to Feishu, optionally applying public or copy/download permissions, or requesting JSON upload results for automation or the Obsidian plugin direct-share flow.
permission
Use when changing Feishu document visibility, copy permissions, or download permissions for an uploaded document token.
delete
Use when removing a Feishu document by token and cleaning the matching entry from local obshare-cli upload history.