Borrowing it
Nothing to install: this file belongs to victoriacity/openakari. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/victoriacity/openakari/main/.claude/skills/diagnose/SKILL.mdgit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/diagnose)<a href="https://agentmods.dev/skills/victoriacity/openakari/diagnose"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/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/victoriacity/openakari/diagnose"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/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 | $0.00015 | $0.01846 |
| Opus 5.5 | $0.00006 | $0.00738 |
| Sonnet 5.5 | $0.00003 | $0.00369 |
| Haiku 4.5 | $0.00002 | $0.00185 |
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 2mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/diagnose
You are diagnosing empirical results — finding patterns in errors, generating hypotheses about root causes, and assessing whether the results mean what they appear to mean. This is the analytical complement to /synthesize (which works across accumulated findings); /diagnose works within one result set.
The argument is a path to results (CSV, log entry, analysis output) or a description of what to examine. Read the data first.
When to use this vs alternatives
- Use
/diagnosewhen you have empirical results (CSVs, metrics, error logs) and want to understand what they mean — error patterns, root-cause hypotheses, validity assessment. - Use
/postmortemwhen the problem is not "what do the results mean?" but "why did an agent report flawed results as correct?" Postmortem analyzes reasoning failures; diagnose analyzes data. - Use
/review metricswhen you suspect the metrics themselves may be degenerate or misleading before interpreting the results./reviewchecks whether results are interpretable;/diagnoseinterprets them.
Step 1: Understand the experiment
- Read the results file and any associated project log entries.
- Identify what was measured, what was varied, and what the expected outcome was.
- Read the experiment design or method description if one exists.
- Identify which CI layers are involved.
Step 2: Characterize the error distribution
Do not start with individual examples. Start with the distribution:
- Overall rates: What is the base rate of success/failure? How does it compare to random chance or a naive baseline?
- Conditional rates: Break errors down by every available dimension (model, question type, category, run number, etc.). Where are errors concentrated?
- Error types: Categorize errors. Are they systematic (same direction, same condition) or random (scattered)? Common categories for judgment tasks:
- Wrong direction (picked A when B was correct)
- False consensus (called a tie when humans disagreed)
- False distinction (picked a winner when humans saw a tie)
- Magnitude error (correct direction but wrong confidence)
- Temporal patterns: Do error rates change over runs? Is there a position effect, order effect, or fatigue analog?
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.
- 2mo ago First seen · 159 lines · 15 tokens per session scan A 5fdac93b826f
diagnose is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 1,846 once invoked, about $0.0001 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
trace
Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.
pos-tagging-fixes
Diagnose and fix part-of-speech tagging in the compromise source repository. Choose between lexical data, ambiguity clues, indexed neighbour rules, preTagger logic, and postTagger patterns with attention to execution order, side effects, runtime, and bundle size. Use for internal tagging changes, not ordinary…
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
linear-solvers
Select and configure linear solvers for systems Ax=b in dense and sparse problems. Use when choosing direct vs iterative methods, diagnosing convergence issues, estimating conditioning, selecting preconditioners, or debugging stagnation in GMRES/CG/BiCGSTAB.
nonlinear-solvers
Select and configure nonlinear solvers for f(x)=0 or min F(x). Use for Newton methods, quasi-Newton (BFGS, L-BFGS), Broyden, Anderson acceleration, diagnosing convergence issues, choosing line search vs trust region, and analyzing Jacobian quality.
numerical-stability
Analyze and enforce numerical stability for time-dependent PDE simulations. Use when selecting time steps, choosing explicit/implicit schemes, diagnosing numerical blow-up, checking CFL/Fourier criteria, von Neumann analysis, matrix conditioning, or detecting stiffness in advection/diffusion/reaction problems.