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 commands/adilkalam/orca/ios-impeccablegit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/commands/adilkalam/orca/ios-impeccable)<a href="https://agentmods.dev/commands/adilkalam/orca/ios-impeccable"><img src="https://agentmods.dev/badge/commands/adilkalam/orca/ios-impeccable.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 | $0.00177 | $0.04139 |
| Opus 5 | $0.00088 | $0.02070 |
| Sonnet 5 | $0.00035 | $0.00828 |
| Haiku 4.5 | $0.00018 | $0.00414 |
Grade A, and why
ios-impeccable 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 4d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ios-impeccable — iOS/SwiftUI Design Lane (three tiers)
The canon is ~/.claude/docs/reference/design-lane.md — the tier model, the precedence order
(owner > aesthetic > detector), the aesthetic-capture protocol, and the shared T1/T2 mechanics are
defined THERE, once. This command routes a .swift design request to a tier and executes it with
the iOS deltas below. It restates nothing from the canon except the T0 banned-core (§2 —
deliberately inlined so T0 never depends on a skill load).
Additive composition: /ios-impeccable is an OVERLAY, not a replacement. /ios keeps owning
correctness / architecture / build / visual; this lane owns aesthetic / felt-state / design-DNA
(ios-design-validator fills the design-dna-guardian role for iOS). Neither blocks the other.
1. Routing
Explicit flags are deterministic:
| Argument | Tier |
|---|---|
--tweak |
T0 (§2) |
--layout --typeset --colorize --bolder --quieter --delight --harden --polish --distill --adapt --clarify --animate |
T1 (§3) for that verb |
--full |
T2 (§4) |
Freeform (no flag): classify in one line, then go — a well-defined single-verb intent -> T1; multi-verb / thin brief / whole-screen -> T2.
BIAS-TO-FAST (canon §Routing): when in doubt, route DOWN a tier. Wrong-fast is caught instantly by the owner's live eye on the simulator; wrong-slow burns 20 minutes of machinery on a one-line change.
Excluded from the iOS subset: --overdrive and --threejs (no clean SwiftUI analogue —
Metal/SceneKit is out of scope), and --optimize (also excluded — it was silently dropped from the
iOS verb list before; that exclusion is now explicit). If the owner asks for one, say so and offer
the nearest verb (delight/animate for motion energy, harden/polish for optimize-type asks).
The standalone verb skills (/layout, /typeset, ...) are in-thread craft references WITHOUT the
judge or the detector floor — NOT an enforced path. Enforcement (fresh judge + gate + hook floor)
exists only here: /ios-impeccable --<verb> (T1) or T2.
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.
- 4d ago First seen · 215 lines · 177 tokens per session scan A ab8bb7469d1d
ios-impeccable is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 4,139 once invoked, about $0.0009 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 2026-08-31.
Other commands, from other repositories
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
define-events
Produces instrumentation specification with events, properties, owners, and QA steps.
hypothesis
Generate hypotheses and define how to test them.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
question-mode
When this command is used, switch to the specified operational mode. Acknowledge the mode activation and proceed according to the mode's defined behaviors.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.