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.
git clone --depth 1 https://github.com/markdavidgan/apple-dev-skillsWrote 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/markdavidgan/apple-dev-skills/fit-check)<a href="https://agentmods.dev/commands/markdavidgan/apple-dev-skills/fit-check"><img src="https://agentmods.dev/badge/commands/markdavidgan/apple-dev-skills/fit-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/markdavidgan/apple-dev-skills/fit-check"><img src="https://agentmods.dev/badge/commands/markdavidgan/apple-dev-skills/fit-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00120 |
| Opus 5.5 | $0.00009 | $0.00048 |
| Sonnet 5.5 | $0.00005 | $0.00024 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
fit-check 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 1mo 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
Run the architecture-fit-check skill on $ARGUMENTS (default: the subsystem touched by the current change, or the design under discussion).
Produce the five-question audit, a fit verdict (fits / mismatch / needs-observability), and — if mismatched — the fitting primitive from the decision matrix plus the cheapest falsifiable spike to prove the substrate before committing.
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.
- 1mo ago First seen · 9 lines · 23 tokens per session scan A 9275e746126b
fit-check is a command published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 120 once invoked, about $0.0001 per session on Opus 5.5. 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
focused-fix
Apply a focused, minimal-change bugfix with minimal blast radius.
agent-fix-bug
A strict brief that makes a coding agent find the root cause of a bug, fix it minimally, and prove it is fixed.
root-cause-analysis
Find the real root cause of a problem with the 5 Whys, getting past symptoms to the systemic fix.
analyze-performance
Diagnose a performance problem from measurements rather than intuition, and propose the fix with the largest expected return.
bug-report-triage
Turn a vague bug report into a structured, actionable ticket with severity and next steps.
debug-error
Diagnose an error methodically from the message, code, and context, with the most likely cause first.