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 jonZlotnik/how-to-agent --skill broken-windowsgit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/jonzlotnik/how-to-agent/broken-windows)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/broken-windows"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/broken-windows/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/jonzlotnik/how-to-agent/broken-windows"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/broken-windows.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 | $0.00062 | $0.00571 |
| Opus 5 | $0.00031 | $0.00285 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
broken-windows 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Broken Windows
One unfixed defect signals that defects are tolerated here, and the rate of new defects rises to match. The fix isn't a heroic cleanup sprint — it's a posture: when you see a broken window, you do one of three things, but never zero.
When to use
- Opening a file you're about to edit and spotting rot
- Code review surfaces a small smell adjacent to the change
- A test is skipped/xfail'd and you can't tell why
- You're about to add a TODO without an owner or date
Protocol
For each broken window, pick exactly one — never skip:
- Fix now — if the cost is minutes and the scope is local. Comment-out dead code? Delete it. Confused name? Rename. Stale import? Remove.
- File and link — if the fix is non-trivial, open a ticket and leave a one-line code comment pointing to it. Future readers know it's seen, not abandoned.
- Accept with reason — if it's deliberate, say so in a comment:
// kept for backwards compatibility with v1.x clients, remove after 2026-12. Acceptance with a date is fine; silent acceptance is not.
The forbidden fourth option is "walk past and say nothing".
Common windows worth fixing-now
- Commented-out code older than a week → delete (git remembers)
TODO/FIXMEwithout owner or condition → add one or remove the marker- Skipped test → unskip, delete, or document the skip with a follow-up
- A function that returns success on every failure path
- A doc block that disagrees with the code
Red flags (rationalizations to reject)
- "Not my code, not my problem." — You're editing here; right now it is.
- "Cleanup is out of scope." — Three lines of cleanup expand scope by minutes. Pretending you didn't see expands it by months.
- "There are too many to fix all of them." — There are. Fix one. Then the next file you open has one fewer.
Composes with
- [[dry-audit]] — duplicated knowledge is a recurring window.
- [[orthogonality-check]] — quiet coupling growth is the most expensive window.
- [[listen-to-nagging-doubts]] — a vague "this file feels bad" reaction is often a window cluster.
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 · 46 lines · 62 tokens per session scan A 045c11e2d227
broken-windows is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 571 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.