Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/emiliosheinz/agent-skillsnpx agentmods add skills/emiliosheinz/agent-skills/diagnoseWrote 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/emiliosheinz/agent-skills/diagnose)<a href="https://agentmods.dev/skills/emiliosheinz/agent-skills/diagnose"><img src="https://agentmods.dev/badge/skills/emiliosheinz/agent-skills/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/emiliosheinz/agent-skills/diagnose"><img src="https://agentmods.dev/badge/skills/emiliosheinz/agent-skills/diagnose.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 | $0.00102 | $0.03330 |
| Opus 5 | $0.00051 | $0.01665 |
| Sonnet 5 | $0.00020 | $0.00666 |
| Haiku 4.5 | $0.00010 | $0.00333 |
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 11d 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.
2. **curl / HTTP script** against a running dev server. How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose
Goal: find and verify the root cause of a bug, then save a concrete, actionable fix proposal as a persistent artifact.
Hard rule — you diagnose, you do not fix. Never edit application code to make the bug go away. The fix goes in the report as a proposal; applying it is a separate step, taken only after the user has reviewed. Temporary instrumentation (tagged debug logs, a throwaway harness) is allowed and gets cleaned up before you finish.
When to reach for it: when the cause is unknown and the bug is hard — intermittent, subtle, cross-system, or it already survived one wrong fix. Diagnose goes deep (parallel probes, adversarial confirmation) and stops at a reviewed proposal. For a bug you already understand and just want to fix, skip this and fix it directly.
Orchestration (subagent contract)
Diagnosis is where independent, parallel perspectives pay off most: an agent that grades its own reasoning tends to pass it, and hypotheses probe faster in parallel than one at a time. Use subagents under one contract:
- One level of delegation. Subagents do not spawn subagents.
- Stateless. Put everything a subagent needs in its prompt: the repro command, the one hypothesis it owns, the file:line evidence, what a pass/fail looks like. It shares none of your context.
- Compact returns. A subagent returns a structured verdict (below), not raw logs. Anything over ~100 lines goes to a file; it returns the path.
- Isolate shared state. Parallel probes are safe only when they do not fight over the same mutable resource (one dev server, one DB row, one port). Probes that need exclusive access run sequentially, or each in its own git worktree / fixture.
- Workflow is an optional speed-up for dispatching the fan-out where the runtime supports it. Plain sequential subagent calls always work as a fallback — never require Workflow.
- Match model tier and effort to each probe — it's the primary cost lever (below).
AskUserQuestionfor intake, one question at a time, with a recommended default. Fall back to a single plain-text question. Never bundle unrelated questions.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 259 lines · 102 tokens per session scan A 23f8a65a6dd4
diagnose is a skill published in the GitHub repository emiliosheinz/agent-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 3,330 once invoked, about $0.0005 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 2026-08-30.
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.