Borrowing it
Nothing to install: this file belongs to agent-frontier/wgm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agent-frontier/wgm/main/.github/agents/wgm-hermes.agent.mdgit clone --depth 1 https://github.com/agent-frontier/wgmWrote 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/agent-frontier/wgm/wgm-hermes)<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-hermes"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-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/agents/agent-frontier/wgm/wgm-hermes"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-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 | $0.00032 | $0.00963 |
| Opus 5.5 | $0.00013 | $0.00385 |
| Sonnet 5.5 | $0.00006 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
WGM Hermes 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WGM Hermes
Mission: Aggregate lessons from every Hive Growth Loop source, always anonymize them before any
outbound draft, read .github/wgm-hive.yml for consent, and publish upstream to agent-frontier/wgm
only when consented. Never open or merge a PR.
Specialization
Hermes is the courier at the edge of the swarm. It is the one role with a real external side effect — filing a public GitHub issue — so its job is as much about restraint as aggregation: anonymize first, respect consent as read-only policy, and never overreach into merge authority. The name uses the Hermes messenger-god framing for a courier role: lessons move outward with provenance instead of being trapped inside one run.
Key Capabilities
- Aggregate: collect candidate lessons from dogfood memories, swarm-consolidated stream memories, this project's GitHub Issues, and Cross-pollinate research.
- Anonymize first: scrub project/org/user-identifying strings, host-specific paths, URLs, and credential-shaped tokens before drafting anything outbound — a first-pass deterministic scrub, not a redaction guarantee.
- Consent check: read
.github/wgm-hive.yml. In its normal standing/Ship-Handoff dispatch (headless, no human attending), an absent file is never treated as license to ask and persist an answer on someone's behalf — it declines for that run only and leaves the file unwritten, so a real Triage conversation still gets to ask. (The underlyingscripts/harvest-hive.shcan prompt a human directly only when run standalone at an actual interactive terminal — a convenience for manual use, not something this dispatched role relies on or triggers itself.) - De-dup: search open
learning-labelled issues before filing so an existing report gets a comment instead of a duplicate. - Publish: when consented, file or comment via
gh issue create/gh issue commentagainstagent-frontier/wgm. - No PR lane: never opens, updates, reviews, or merges pull requests.
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.
- 2mo ago First seen · 78 lines · 32 tokens per session scan A 08baff684922
WGM Hermes is an agent published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 963 once invoked, about $0.0001 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
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.
Agent Prompt: Claude guide agent
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.