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 melodic-software/claude-code-plugins --skill diagnosegit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/diagnose)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/diagnose"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/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/melodic-software/claude-code-plugins/diagnose"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/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 | $0.00184 | $0.01370 |
| Opus 5.5 | $0.00074 | $0.00548 |
| Sonnet 5.5 | $0.00037 | $0.00274 |
| Haiku 4.5 | $0.00018 | $0.00137 |
Grade A, and why
diagnose 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Claude Code ships computer use as a built-in MCP server whose tool descriptions already cover the mechanics: actions, the allowlist gate, permission tiers, the ladder that prefers a dedicated MCP over Chrome over screen control. This skill does not restate any of that.
It carries only what the surface does not tell you and the model cannot derive: the shape of the screenshot budget, the failure modes that look like tool bugs but are environment state, and the per-OS input quirks that are invisible until they bite.
Arguments
Parse $ARGUMENTS. Each value names one reference spoke; there are exactly three.
| Argument | Loads |
|---|---|
| (none) | Nothing. Answer from the symptom guide below, and load a spoke only if the symptom needs it. |
screenshots |
reference/screenshots-and-zoom.md. Pixel budget, zoom, resolution guidance |
failures |
reference/failure-diagnostics.md. The idle timer, capture and input ladders, probes |
quirks |
The per-OS file for the machine you are on (see below) |
Symptom guide (no file load needed)
| Situation | Answer |
|---|---|
| Screenshot looks low-resolution | Expected. Fixed pixel budget, no setting. Use zoom. → screenshots-and-zoom.md |
| Small text unreadable after downscale | zoom the region. It re-captures at full resolution. Do not lower display resolution. |
empty capture (0x0) |
Environment, not a tool bug. Walk the ladder → failure-diagnostics.md |
| Input returns a UIPI error | An elevated or secure-desktop process holds the foreground. Not recoverable by retrying. |
| "not in the allowed applications and is currently in front" | A background app stole focus. Retry with screenshot as the batch's first action. |
| Session died partway through a long task | Idle timeout. Claude's own input does not reset it → failure-diagnostics.md |
| A synthesized key does nothing in a menu | Shell-owned surfaces differ from in-app menus → your OS's quirks file |
What ships with it
4 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.
- 5d ago Changed · -3 lines 47afdf5a5563
- 1mo ago Changed · +2 lines 661a650391c2
- 1mo ago Changed 39dffa40a205
- 1mo ago Changed 329e51ea570d
- 1mo ago First seen · 88 lines · 184 tokens per session scan A 755bffe8b9b7
diagnose is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 184 tokens to every session and 1,370 once invoked, about $0.0007 per session on Opus 5.5. 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
adversarial-analysis
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
benchmark-before-optimize
For performance work: measure before changing, profile to find bottlenecks, compare before and after.
validate-before-process
For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.
display-grid-state
For 2D debugging: visualize grid/board state, show puzzle progress, make algorithm behavior visible.
handle-edge-cases
For boundary conditions: empty collections, zero values, recursive base cases, null checks, prevent crashes at edges.
claim-check
Claim checker that audits a coding agent's statements that tests pass or a build is clean against its own session transcripts: whether a matching run happened before the claim, whether it passed, and whether code changed after it. Use when the user asks whether the agent really ran the tests, how often it said tests…