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/termio-sh/termio/code-cleannpx skills add termio-sh/termio --skill code-cleangit clone --depth 1 https://github.com/termio-sh/termioWhat 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 | $0.00110 | $0.01775 |
| Opus 5 | $0.00055 | $0.00888 |
| Sonnet 5 | $0.00022 | $0.00355 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
code-clean 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Clean
Two passes over termio's Swift: dead code (symbols nothing reaches) and over-long comments (prose that outgrew what it explains). Both end in a build. Neither is a refactor.
This is not a generic AI-slop sweep. Run one on this repo and it finds nothing:
a 2026-08 survey of all 69k tracked Swift lines turned up 1 TODO (a false
match on an mktemp template), 0 commented-out code blocks, and 1
deliberate debug print. Don't spend the pass hunting those. The bloat here is
shaped differently, and §2 is where it lives.
Scope
Default to the current branch's diff against origin/main. A whole-tree pass is
a standing request only — say so, and expect it to take real time.
Never touch:
Sources/termio/Editor/Highlightr/— vendored; upstream API surface is kept intact on purpose (AGENTS.md).- Anything under
skills/recorded inskills-lock.json— re-pull from upstream instead of hand-editing. ios/build/,ios/build-sim/— Xcode artifacts, not tracked source. They hold ~100k lines of SPM checkouts that will swamp any tree-wide grep. Scope greps withgit ls-files, never barefind ios.
1. Dead code
periphery scan --targets termio (SPM; no config file needed). It is installed
at /opt/homebrew/bin/periphery.
Roughly three of every four hits are false. Four shapes account for nearly all of them — clear each before deleting anything:
- Retain-holders.
private var toolbarDelegate / menuBar / hookListener / linkClickMonitor / scanTask / stream / source / window. FlaggedassignOnlyProperty, but holding the reference is the job — drop the property and the object deallocates and the feature dies.App.swiftsays so in comments ("must be retained"). Equatable/Hashablekey-struct fields. Read only through the synthesized==/hash(into:), which periphery cannot see.BranchModel'sGitStatespells out why its field exists: so a same-HEAD refresh is recognized as a no-op.@objcselector-targetsender:parameters. The AppKit selector signature requires them.- Vendored code. See Scope.
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 First seen · 151 lines · 110 tokens per session scan A 1ff886f0845a
code-clean is a skill published in the GitHub repository termio-sh/termio (359 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 1,775 once invoked, about $0.0006 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
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
argent-settings-permissions
Grant, deny, or reset an app's runtime permissions (camera, microphone, photos, contacts, notifications, calendar, location, location-always, media-library, motion, reminders) on an iOS simulator or Android device using the argent settings-permissions tool - without navigating the system Settings UI. Use when the…
argent-lens
Propose multiple visual design variants for on-screen elements and let the human pick in the Argent Lens window. Use when the user asks for design alternatives / options / A-B choices for a screen or component, or any time you have produced more than one candidate look for an element and want a human decision before…
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.
argent-screenshot-diff
Compare saved or live app screenshots with the argent screenshot-diff tool. Use when testing visual regressions, before/after UI comparisons, screenshot diff checks, visible layout, spacing, color, typography, clipping, overflow, text rendering, or image/icon rendering changes.
argent-react-native-profiler
Profile a React Native Hermes app to measure re-render and CPU performance using argent profiler tools. Use when optimizing for performance, measuring before/after a fix, spotting slow components, diagnosing re-renders, checking CPU hotspots, or producing a ranked issue report.