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 agentmods add skills/melodic-software/claude-code-plugins/diagnosenpx skills add melodic-software/claude-code-plugins --skill diagnosegit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWhat 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 | $0.00184 | $0.01339 |
| Opus 5 | $0.00092 | $0.00669 |
| Sonnet 5 | $0.00037 | $0.00268 |
| Haiku 4.5 | $0.00018 | $0.00134 |
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 2d 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 — 88 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.
- 2d 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 (12 stars, last pushed 2d ago), licensed MIT. It adds 184 tokens to every session and 1,339 once invoked, about $0.0009 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
deep-research
Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore…
error-ux
Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.
adversarial-patterns
Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.
documentation-testing
Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.
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.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.