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 Justinmendezai/The-Adam-Repo --skill diagnosegit clone --depth 1 https://github.com/Justinmendezai/The-Adam-RepoWrote 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/justinmendezai/the-adam-repo/diagnose)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/diagnose"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/diagnose/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/justinmendezai/the-adam-repo/diagnose"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/diagnose.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 | $0.00051 | $0.00790 |
| Opus 5 | $0.00026 | $0.00395 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
diagnose scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- A `curl` command that returns the wrong output, or How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diagnose
Adapted from Matt Pocock's diagnose. Stops the "try random fixes" anti-pattern.
The loop
1. REPRODUCE — get a reliable repro
2. MINIMIZE — strip the repro to the smallest case that still fails
3. HYPOTHESIZE — name a single concrete hypothesis
4. INSTRUMENT — add the cheapest probe that confirms or refutes it
5. CONFIRM — run; read the output; the hypothesis is true or false
6. FIX — change the smallest thing that resolves the cause
7. REGRESS — write a test that would have caught this
Each step has a clear pass/fail. If you skip ahead, you're guessing.
REPRODUCE
You don't have a bug; you have a story about a bug. Convert the story to a script:
- A failing unit test, or
- A
curlcommand that returns the wrong output, or - A click sequence in
cursor-ide-browserthat yields the wrong screen.
If you can't reproduce, you can't diagnose. Time spent hunting a repro is never wasted.
MINIMIZE
Now strip everything not necessary to the failure:
- Removing a dep — does it still fail?
- Removing a function call — does it still fail?
- Smaller input — does it still fail?
Stop when removing one more thing makes the bug disappear.
HYPOTHESIZE
Write down one sentence: "The bug is caused by X." Not "It might be X or Y or Z." Pick one. The next step will prove or disprove it.
INSTRUMENT
Add the cheapest probe:
- A
console.logat the suspected branch. - A breakpoint in the debugger.
- A query against the DB to check actual stored state.
- A network log via the logger MCP.
The probe should produce a one-line yes/no answer to the hypothesis. If it can't, simplify the hypothesis.
CONFIRM
Run. Read. Either:
- The hypothesis is true → proceed to FIX.
- The hypothesis is false → form a new hypothesis. Do not skip back to a fix; re-enter HYPOTHESIZE.
FIX
Smallest possible change. If you're tempted to "also fix" something else nearby, stop. Open a separate slice or note.
REGRESS
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.
- 12d ago First seen · 90 lines · 51 tokens per session scan A 6c54bc0c9e8d
diagnose is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 51 tokens to every session and 790 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.