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 skills/anomalyco/hex/hex-personal-commandsnpx skills add anomalyco/hex --skill hex-personal-commandsgit clone --depth 1 https://github.com/anomalyco/hexWrote 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/anomalyco/hex/hex-personal-commands)<a href="https://agentmods.dev/skills/anomalyco/hex/hex-personal-commands"><img src="https://agentmods.dev/badge/skills/anomalyco/hex/hex-personal-commands.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 | $0.00044 | $0.00722 |
| Opus 5 | $0.00022 | $0.00361 |
| Sonnet 5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
hex-personal-commands 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 2d 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.
What it actually says
HEX Personal Commands
Use HEX's managed command workspace rather than creating an independent package.
- Check for
~/.config/hex/hex.config.ts. If it is missing, ask the user to open HEX's Commands pane and choose Create Config. If thehexCLI is available,hex commands initperforms the same provisioning. Bun must be installed separately. - Read
~/.config/hex/AGENTS.mdand~/.config/hex/.agents/skills/personal-commands/SKILL.md. Check.hex-sdk/package.jsonand its exported declarations for the installed API and exact Effect requirement; scaffolded instructions are not overwritten on upgrades and may be older than the SDK. - Edit only user-owned workspace files, normally
hex.config.ts. Never edit.hex-sdk; HEX refreshes that managed SDK from the app bundle. - Use
defineHexConfigfrom@hex/commandsfor Promise handlers, dictation controls, and transformations. For Effect handlers, importdefineHexConfigandHexfrom@hex/commands/effect, and Effect APIs fromeffect. - Keep command phrases unambiguous and use only the capabilities required by
the request. Treat config and dependencies as trusted executable code with
the user's filesystem, network, environment, and subprocess authority.
Use
digit()for zero through nine,digit({ min, max })for a restricted range,choice(["left", "right"] as const)for exact choices, an object-formchoice()to normalize one-word aliases to canonical keys,union(letter(), digit(), choice(["home", "end"] as const))for disjoint bounded one-token alternatives, and trailingtext()for explicit text captures.letter()accepts literal, common spoken, and one-word NATO letter names and returns lowercase"a" | ... | "z". With acapturesschema, every phrase alias must bind every declared name exactly once. - Spoken commands and dictation controls need the Commands opt-in, which defaults off; creating a config does not enable it. Transformations must be selected in the mode's Transformations section and can run with Commands off. They run after mode corrections and optional AI rewriting, not for Voice Action or meetings. Do not enable voice commands merely to run a transformation.
- Run
bun run checkin~/.config/hex. Do not finish until it passes. This checks TypeScript; runtime validation can still reject phrase overlaps. A running host watches workspace.tsand.jsonfiles and reports reload failures in the Commands pane. If startup stopped because the config, Bun, or dependencies were unavailable, restart HEX after repairing them. Confirm runtime activation when the host is enabled, or report that it was not tested.
Completion criterion: the requested behavior is represented in
hex.config.ts, the managed SDK was not modified, bun run check passes, and
runtime activation is confirmed or its verification gap is reported.
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.
- 2d ago Changed · +11 lines b25bddf26fd4
- 6d ago First seen · 40 lines · 44 tokens per session scan A 188804e706de
hex-personal-commands is a skill published in the GitHub repository anomalyco/hex (130 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 722 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
os-rust-backend
Use when working on a Rust backend that follows the Open Software Network house style — the seven-crate Cargo workspace split (domain / services / persistence / providers / config / api / app) shared by os-accounts and os-platform (fellow). Trigger on: scaffolding a new service in this org ("like os-accounts"…
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.