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 davidgut1982/hermes-toolkit --skill hermes-fork-maintainergit 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/skills/davidgut1982/hermes-toolkit/hermes-fork-maintainer)<a href="https://agentmods.dev/skills/davidgut1982/hermes-toolkit/hermes-fork-maintainer"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-fork-maintainer/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/davidgut1982/hermes-toolkit/hermes-fork-maintainer"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-fork-maintainer.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 | $0.00174 | $0.01755 |
| Opus 5.5 | $0.00070 | $0.00702 |
| Sonnet 5.5 | $0.00035 | $0.00351 |
| Haiku 4.5 | $0.00017 | $0.00176 |
Grade B, and why
hermes-fork-maintainer scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo ~/.claude/skills/hermes-fork-maintainer/scripts/hermes-triage.sh --assert # exit 0 = safe How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Fork Maintainer
A personal Hermes fork is a distribution: upstream main plus a stack of
feature PRs merged into one integration branch. When the fork is deployed as an
editable install, there is no build step — the checked-out git branch IS the
running code. (This setup example: [email protected]:<your-fork>/hermes-agent.git, the
integration branch is integrated, the live editable install is at
/opt/hermes/home/.hermes/hermes-agent — substitute your own fork URL and host.)
The deploy invariant (read first, every time)
The live tree MUST stay on the integration branch (
integrated).git checkout <feature-branch>on the live tree silently swaps the running agent's code. Two prior outages were caused exactly this way.
- NEVER
git checkouta feature branch on the live checkout. - Do dev/PR work in a
git worktree(/opt/hermes/dev/hermes-agentis the existing dev split here) or under a dev profile. - After ANY operation, confirm
git -C <live> branch --show-current==integrated. - Paths under
/opt/hermes/are root-owned: run git/the upgrade script withsudo.
Run the integrity check before AND after any fork work (env-overridable; defaults to this setup):
sudo ~/.claude/skills/hermes-fork-maintainer/scripts/hermes-triage.sh --assert # exit 0 = safe
Quick reference
| Task | Path |
|---|---|
Live tree (must stay integrated) |
/opt/hermes/home/.hermes/hermes-agent |
| Dev worktree (PR work happens here) | /opt/hermes/dev/hermes-agent |
| Upgrade driver (does steps 1–12) | /opt/hermes/home/.hermes/upgrade-hermes.sh |
| Distribution changelog | CHANGELOG.integrated.md |
| origin (push) | davidgut1982/hermes-agent |
| upstream (fetch only) | NousResearch/hermes-agent |
The upgrade flow
The fork ships its own driver — NEVER run hermes update (it resets the clone
to origin/main and DESTROYS the integration branch). Run the driver instead:
sudo /opt/hermes/home/.hermes/upgrade-hermes.sh
What ships with it
4 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.
- 2mo ago First seen · 139 lines · 174 tokens per session scan B 77e9e36d135f
hermes-fork-maintainer is a skill published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 5mo ago), licensed MIT. It adds 174 tokens to every session and 1,755 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
hermes-fork-maintainer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-fork-maintainerdavidgut1982/hermes-toolkit | Skill | 2 | 5mo ago | MIT | B | 174 | Claude Code, Codex |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 6d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | today | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | today | MIT | A | 20 | Claude Code, Codex |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | 2d ago | MIT | A | 51 | Claude Code |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |