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-debuggit 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-debug)<a href="https://agentmods.dev/skills/davidgut1982/hermes-toolkit/hermes-debug"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-debug/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-debug"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-debug.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 | $0.00162 | $0.01538 |
| Opus 5.5 | $0.00065 | $0.00615 |
| Sonnet 5.5 | $0.00032 | $0.00308 |
| Haiku 4.5 | $0.00016 | $0.00154 |
Grade B, and why
hermes-debug 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-debug/scripts/hermes-triage.sh How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Debug
A misbehaving Hermes install almost always traces to one of eight known causes. Work the checklist in order — each step is cheap and the early ones catch the most common (and most destructive) faults. Stop at the first one that explains the symptom.
Run the fast triage first; it answers steps 1, 2, and 7 in one shot (env-overridable; defaults to the author's homelab setup):
sudo ~/.claude/skills/hermes-debug/scripts/hermes-triage.sh
On this install, ops uses the cluster-ops MCP (service_status, journal_tail,
disk_usage, docker_ps, exec_raw, cluster_snapshot) — terminal AND
code_execution are in agent.disabled_toolsets, so shelling out from the agent
will not fire. Substitute your own ops mechanism if yours aren't disabled.
The ordered checklist
| # | Symptom | Check | Fix |
|---|---|---|---|
| 1 | Old behavior persists; code "didn't change"; weird crashes after dev work | git -C /opt/hermes/home/.hermes/hermes-agent branch --show-current |
must be integrated. If not, git checkout integrated + pip install -e .. #1 gotcha — editable install: the branch IS the running code. |
| 2 | Config edit had no effect on one surface | which file did you edit? | TWO config files drift — fix BOTH (see below). |
| 3 | Model returns 404 / provider error | profile's provider + model valid? |
provider must exist; deepseek profiles need provider: openrouter; check credential-pool contamination. references/provider-routing.md. |
| 4 | A status check costs 6-17 model calls / times out | was it delegated? | simple ops must go DIRECT to a cluster-ops tool, never delegate_task. references/delegation-explosion.md. |
| 5 | Extra discovery round-trips before a tool fires | is tool_search deferring the needed tool? |
pin frequently-used tools so they aren't deferred behind the bridge stubs. |
| 6 | Same prompt fast interactively, slow as a one-shot | warm vs cold path | cold one-shot CLI re-inits MCP every run; benchmark the warm gateway/interactive path. |
| 7 | hermes gateway stop/status says no gateway, but it's running |
PID/lock symlinks | recreate the symlinks (see below). |
| 8 | Runs feel throttled / truncated reasoning | reasoning_effort setting |
check the profile's reasoning_effort isn't choking the model. |
| — | "which city?" on a bare weather query | identity/profile context stripped | the Woodstock default needs context files injected; don't skip_context_files. |
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.
- 2mo ago First seen · 105 lines · 162 tokens per session scan B 04c97836e3ab
hermes-debug is a skill published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 5mo ago), licensed MIT. It adds 162 tokens to every session and 1,538 once invoked, about $0.0006 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-debug compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-debugdavidgut1982/hermes-toolkit | Skill | 2 | 5mo ago | MIT | B | 162 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | today | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 2.0k | 24d ago | MIT | A | 36 | Claude Code |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |