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 rhtevan/agentfs --skill hermes-desktop-fixesgit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/hermes-desktop-fixes)<a href="https://agentmods.dev/skills/rhtevan/agentfs/hermes-desktop-fixes"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/hermes-desktop-fixes.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.01592 |
| Opus 5 | $0.00011 | $0.00796 |
| Sonnet 5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade D, and why
hermes-desktop-fixes scanned grade D with 2 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 8d 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.
**Symptom:** `hermes desktop` prompts for sudo password to set SUID on chrome-sandbox. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.config/Hermes/Local\ Storage/leveldb/* How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Desktop Fixes
Bugs Fixed
0. LC_CTYPE Locale Warning (Cosmetic, Annoying)
Symptom: bash: warning: setlocale: LC_CTYPE: cannot change locale (UTF-8): No such file or directory — appears 6× in the Desktop in-app terminal on every shell start.
Root cause: Electron inherits macOS-style LC_CTYPE=UTF-8 (bare, no language prefix like en_US.). Bash calls setlocale() during startup before any profile/rc file is sourced, so .bashrc fixes are too late.
Fix: Three layers (belt-and-suspenders):
~/.hermes/.env—LC_CTYPE=en_US.UTF-8(loaded byload_hermes_dotenv()before spawning terminals)~/.hermes/hermes-env.sh— conditional export whenLC_CTYPEis "UTF-8" or empty~/.config/environment.d/50-locale-fix.conf— systemd user env (applies to new login sessions) Note: The.bash_profileearly-export approach does NOT work — bash'ssetlocale()fires before any profile is sourced.
1. Provider Identity Loss (Critical)
Symptom: "No LLM provider configured" on new Desktop sessions; CLI works fine.
Root cause: _session_info() in tui_gateway/server.py reports agent.provider = "custom" (resolved generic) instead of "custom:litellm-vertex-ai". Desktop caches this bare "custom" in localStorage, sends it on next session.create. _get_named_custom_provider("custom") returns None → falls through → no provider.
Fix: _resolve_session_info_provider(agent) helper maps bare "custom" back to custom:<name> via find_custom_provider_identity(base_url).
2. Goose Node Wrapper Breaks Builds
Symptom: npm/electron-builder fails with CWD errors.
Root cause: /usr/lib/Goose/resources/bin/node wrapper does cd ~/.config/goose/mcp-hermit before running real node.
Fix: hermes-env.sh strips it from PATH.
3. Electron Sandbox Requires Sudo
Symptom: hermes desktop prompts for sudo password to set SUID on chrome-sandbox.
Root cause: _desktop_linux_sandbox_fixup() in hermes_cli/main.py requires root.
Fix: Early return when ELECTRON_DISABLE_SANDBOX=1 is set. Env var set in hermes-env.sh and .env.
What ships with it
2 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.
- 8d ago First seen · 100 lines · 22 tokens per session scan D 91a5dcb4c537
hermes-desktop-fixes is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.