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 skills add sjarmak/coding-agent-workflows --skill repo-architecture-reviewgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/repo-architecture-review)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/repo-architecture-review"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/repo-architecture-review/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/skills/sjarmak/coding-agent-workflows/repo-architecture-review"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/repo-architecture-review.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 | $0.00101 | $0.00973 |
| Opus 5 | $0.00051 | $0.00487 |
| Sonnet 5 | $0.00020 | $0.00195 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
repo-architecture-review 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Architecture Review
Analyze a repository from the perspective of long-term architecture, not code quality. The goal is to maximize engineering leverage — the ratio of future work made easier to effort spent — not to produce the largest refactor.
Operating principles
- Assume the existing developers are competent. A design you don't understand usually encodes a constraint you haven't found yet.
- Explain why a design exists before proposing an alternative. If you can't state the force it solves, you're not ready to change it.
- Prefer understanding over editing. Most of the value is in the map, not the diff.
- Optimize for conceptual simplicity (fewer concepts to hold in your head), not fewer lines.
- Favor deleting a concept over introducing a new abstraction.
- A small, targeted structural improvement beats a large rewrite almost always.
Investigate before judging
Build a mental model first. Read, don't skim; trace one real request/data path end to end. Study:
- system architecture and the dependency graph (what depends on what, and cycles)
- public APIs and module/package boundaries
- information flow and where it bottlenecks through a single choke point
- ownership boundaries (who changes what, and where changes ripple)
- test organization, build system, docs, and examples
- repository history when available — churn hotspots and repeated reverts reveal where the architecture fights its developers
Prefer evidence you can point to (a file, a grep count, an import cycle, a
commit pattern) over impressions.
What to look for
Duplicated concepts · unnecessary coupling · hidden abstractions · information bottlenecks · inconsistent APIs across similar surfaces · the same implementation pattern re-hand-rolled in N places · architectural drift (structure no longer matching intent) · scalability limits · opportunities for shared infrastructure.
Rank by leverage, not size
For each candidate improvement, score it so the ranking is defensible:
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.
- 10d ago First seen · 93 lines · 101 tokens per session scan A f4245d7224ea
repo-architecture-review is a skill published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 9d ago), licensed MIT. It adds 101 tokens to every session and 973 once invoked, about $0.0005 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 skills, from other repositories
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
codex-context-improver
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.