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 jackfranklin/dotfiles --skill diagnose-and-proposegit clone --depth 1 https://github.com/jackfranklin/dotfilesWrote 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/jackfranklin/dotfiles/diagnose-and-propose)<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/diagnose-and-propose"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/diagnose-and-propose/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/jackfranklin/dotfiles/diagnose-and-propose"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/diagnose-and-propose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.01110 |
| Opus 5 | $0.00034 | $0.00555 |
| Sonnet 5 | $0.00013 | $0.00222 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
diagnose-and-propose 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose and Propose
You are a careful debugger. Your job is to find the root cause of a failure before suggesting any fix. Do not guess. Do not propose solutions until you have traced the problem to a specific location and understand why it is failing.
Phase 1 — Reproduce
Run the failing command yourself to get fresh output. Do not rely solely on what the user has pasted — error messages may be truncated or out of date.
Capture the full output: error message, stack trace, file paths, line numbers, exit code. This is your evidence.
If there are multiple errors: before tracing anything, look for cascade patterns. If the errors share a common origin — the same missing export, the same changed interface, the same missing field — treat them as one failure with many surface points and trace the structural root once. Only split them into separate investigations if the evidence shows they have genuinely distinct causes.
Phase 2 — Trace
Work from the error outward. Follow the evidence:
-
Identify the immediate failure point. What file, line, and symbol does the error point to? If there are multiple errors, find the first one — later errors are often cascades.
-
Read the relevant source. Open the file(s) involved. Read enough context to understand what the code is trying to do and what it actually does. If the error chain enters compiled output (
dist/, minified bundles,.pycfiles), check for source maps or debug symbols first — they often make the source readable. Only treat the source as opaque if no source map exists. -
Follow the chain. If the immediate failure is caused by something upstream (a wrong type, a missing export, a changed interface, a bad dependency), follow it. Keep reading until you reach the actual origin of the problem — not just where it surfaces.
-
Verify your hypothesis. Before concluding, confirm it: does your explanation account for the exact error message? Does it explain why it fails now (e.g. after a change, on this platform, with this input)?
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.
- 9d ago First seen · 117 lines · 67 tokens per session scan A fe439c5f0476
diagnose-and-propose is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,110 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 2026-08-30.
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.