Hermex is a native iPhone app for controlling a self-hosted Hermes AI agent running on a server you own. It lets people chat with the agent, manage sessions and scheduled tasks, browse skills and files, and inspect memory from iOS. The catalogue entries are add-ons for the Hermes agent that Hermex connects to.
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 agentmods add agents/uzairansaruzi/hermex/issue-trackergit clone --depth 1 https://github.com/uzairansaruzi/hermexWrote 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/uzairansaruzi/hermex/issue-tracker)<a href="https://agentmods.dev/agents/uzairansaruzi/hermex/issue-tracker"><img src="https://agentmods.dev/badge/agents/uzairansaruzi/hermex/issue-tracker.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 | $0.00000 | $0.00767 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
issue-tracker 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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Tracker: GitHub
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for issue operations.
Repository
- GitHub repo:
uzairansaruzi/hermex - Remote:
https://github.com/uzairansaruzi/hermex.git
Infer the repo from git remote -v when possible; gh does this automatically when run inside the clone.
Conventions
- Create an issue:
gh issue create --title "..." --body "..." - Read an issue:
gh issue view <number> --comments - List issues:
gh issue list --state open --json number,title,body,labels,comments --jq '[.[] | {number, title, body, labels: [.labels[].name], comments: [.comments[].body]}]' - Comment on an issue:
gh issue comment <number> --body "..." - Apply a label:
gh issue edit <number> --add-label "..." - Remove a label:
gh issue edit <number> --remove-label "..." - Close an issue:
gh issue close <number> --comment "..."
Use heredocs for multi-line issue bodies and comments.
Pull Requests as a Triage Surface
PRs as a request surface: no. Bug reports and feature requests belong in issues, not in PR comments. Review comments on an open PR are still actionable — triage and address them as described below.
Branch and PR Workflow
GitHub Issues are the work queue; pull requests are the review and merge record.
- Pick implementation work from issues labeled
ready-for-agent, unless the human selects another issue. ready-for-agentissues default to express mode (autonomous from approved plan to review-addressed PR). An issue also labeledneeds-manual-validationforces staged mode, where the owner manually tests before the PR publishes. Seedocs/agents/triage-labels.md.- Create a short
issue/<n>-slugbranch for one issue or narrow slice (no-issue branches usechore//fix/). - Commit completed, validated work locally with the matching handoff updates.
- Push feature branches and open PRs only when the human asks to publish/open a PR. Open them ready for review, not as drafts: the review bots only run on ready PRs.
- Use the PR for review: GitHub/Copilot review, CI, external agent review, and human comments should live there when possible.
- Address PR review comments by triaging them first; do not blindly accept automated review feedback.
- Merge into
masteronly after validation passes, review feedback is resolved, and the human approves. - Keep
masterbuildable because it is the internal TestFlight candidate branch.
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.
- 6d ago First seen · 53 lines · 0 tokens per session scan A d9d1f297160c
issue-tracker is an agent published in the GitHub repository uzairansaruzi/hermex (1,233 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 767 tokens. 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 2026-08-30.
Other agents, from other repositories
i18n
Multiplex ships English (source), Traditional Chinese (zh-Hant, Taiwan wording) and Japanese (ja). Decisions below were settled 2026-08-18; do not re-litigate without new facts.
input-and-windows
Load-bearing decisions split from AGENTS.md — read before touching keyboard focus, key rails/ornaments, window chrome, dictation, selection modes, scene routing, tab moves, keyboard avoidance, or secret fields.
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.
backends-and-probe
Load-bearing decisions split from AGENTS.md — read before touching TmuxProbe, HerdrProbe, session creation/targeting, or file attach/drop.
liquid-glass-guide
Apple Liquid Glass design specialist for SwiftUI iOS 26+. Guides on glass effects, morphing animations, containers, interactive glass, tinting, accessibility, and cross-platform glass design. Use when building modern Apple UI with Liquid Glass.
agent-helpers
Load-bearing decisions split from AGENTS.md — read before touching AgentSignature, helper chips, launch model overrides, the keychain tip, or HISTORY/jump.