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/JobsHwang/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/jobshwang/skills/arch-scan)<a href="https://agentmods.dev/commands/jobshwang/skills/arch-scan"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/arch-scan/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/jobshwang/skills/arch-scan"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/arch-scan.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 | $0.00024 | $0.00456 |
| Opus 5.5 | $0.00010 | $0.00182 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
arch-scan 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
The user explicitly invoked /arch-scan.
Invocation arguments: $ARGUMENTS
Arch Scan
Turn architectural decay from a vague feeling into a ranked list of candidates. This is a survey, not a rescue.
- Resolve scope before scanning. If the user named a module, subsystem, or pain point, use it. Otherwise read recent commit history (
git log --oneline) and let recurring hot spots pull attention first; deepening pays off most where change keeps happening. - Read the resolved durable spec root (project convention, then
.agents/spec,.trellis/spec, thendocs/spec) before proposing anything. Settled decisions are context, not items to re-litigate. - Explore the scoped area for friction signals, using the vocabulary in references/deep-modules.md:
- understanding one concept requires bouncing between many small modules;
- interfaces nearly as complex as their implementations (shallow modules);
- extractions made purely for testability while the real bugs hide in how they are called (no locality);
- tightly coupled logic leaking across seams.
- Apply the deletion test to every suspect: deleting it should concentrate complexity in the survivors, not scatter it back across callers.
- Write a self-contained Markdown report with Mermaid diagrams to the operating system's temporary directory, never into the workspace. For each candidate include: the files involved, the problem, a plain-language solution, benefits in terms of leverage and locality, a before/after diagram, and a recommendation strength (
strong,worth exploring, orspeculative). End with the single top recommendation and why. - If a candidate contradicts an existing durable spec, only surface it when the friction justifies reopening that decision, and mark the conflict explicitly.
Do not modify code, create repository files, or invoke another Skill. Report the absolute report path, the candidate count, and the top pick. Suggest grill-me on the chosen candidate as the next explicit action; the deepening work itself belongs to to-spec and slice-spec.
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 · 25 lines · 24 tokens per session scan A e2a3c6ba8f1b
arch-scan is a command published in the GitHub repository JobsHwang/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 456 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).