Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
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 NousResearch/hermes-agent --skill githubgit clone --depth 1 https://github.com/NousResearch/hermes-agentWrote 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/nousresearch/hermes-agent/github)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/github"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/github/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/nousresearch/hermes-agent/github"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- 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 45 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 | $0.00019 | $0.00607 |
| Opus 5.5 | $0.00008 | $0.00243 |
| Sonnet 5.5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
github 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub
Work GitHub end to end with the gh CLI (REST fallback where noted): auth,
issues, the PR lifecycle, issue-to-PR delivery, code review, and repo
management. This skill consolidates six former skills; each workflow lives
complete in its reference file — ALWAYS read the matching reference before
starting that workflow, the body below only routes.
Routing
| Task | Read first |
|---|---|
| Auth broken / new machine / token or SSH setup / gh login | references/auth.md |
| Create, triage, label, assign, close issues | references/issues.md |
| Branch, commit, open PR, watch CI, merge | references/pr-workflow.md |
| Carry an ISSUE to a verified PR (full delivery loop) | references/issue-to-pr.md |
| Review someone's PR: diffs, inline comments, verdict | references/code-review.md |
| Clone/create/fork repos, remotes, releases | references/repo-management.md |
Supporting assets: scripts/gh-env.sh + scripts/git-credential-token.py
(auth helpers), templates/ (PR bodies, bug report, feature request),
references/ci-troubleshooting.md, references/conventional-commits.md,
references/github-api-cheatsheet.md, references/review-output-template.md.
Core discipline (applies to every workflow)
- Preflight once per session:
gh auth status— if it fails, go toreferences/auth.mdbefore anything else. - Prefer
ghover raw REST; drop togh apionly for endpoints the porcelain lacks (the cheatsheet lists them). - Never report CI green without checking
gh pr checksyourself; never claim merged without verifyingstate,mergedAt. - Read full context before writing:
gh issue view --comments/gh pr view --comments— decisions live in threads, not titles. - Sweep for duplicates before creating anything:
gh pr list --search/gh issue list --search.
Verification
- The workflow's own reference file defines done for that task.
- Cross-cutting: every claim about remote state (CI, merge, release,
issue state) is backed by a fresh
ghread, never memory.
What ships with it
16 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.
- references/auth.md 11 KB
- references/ci-troubleshooting.md 4.8 KB
- references/code-review.md 13 KB
- references/conventional-commits.md 2.4 KB
- references/github-api-cheatsheet.md 5.9 KB
- references/issue-to-pr.md 5.5 KB
- references/issues.md 8.8 KB
- references/pr-workflow.md 9.5 KB
- references/repo-management.md 13 KB
- references/review-output-template.md 2.4 KB
- scripts/gh-env.sh 2.5 KB runs code
- scripts/git-credential-token.py 1.7 KB runs code
- templates/bug-report.md 469 B
- templates/feature-request.md 598 B
- templates/pr-body-bugfix.md 513 B
- templates/pr-body-feature.md 580 B
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 · 57 lines · 19 tokens per session scan A 9d70e7c842fe
github is a skill published in the GitHub repository NousResearch/hermes-agent (255,268 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 607 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 2026-09-03.
Other skills, from other repositories
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep…
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
otto-drive-pr
PR mergeability, CI, and live preview.
git-story-film
Direct an animated film of about two minutes from a software repository's Git history. Select real commits, releases and reverts; develop the story, character and visual style; build an outline, cast sheet, storyboard and HTML review studio; then render a 4K/60fps MP4 after approval. Use for repository or product…
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
explain-pr
Explain a PR: the background problem and the proposed solution.