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 jhlee0409/omni-harness-kit --skill diagnosegit clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/jhlee0409/omni-harness-kit/diagnose)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/diagnose"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/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/jhlee0409/omni-harness-kit/diagnose"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/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 | $0.00077 | $0.00408 |
| Opus 5 | $0.00039 | $0.00204 |
| Sonnet 5 | $0.00015 | $0.00082 |
| Haiku 4.5 | $0.00008 | $0.00041 |
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 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.
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.
What it actually says
diagnose
Don't guess-and-patch. Find the real cause, then fix it.
Loop
- Reproduce — get a reliable, minimal repro. A bug you can't reproduce, you can't confirm you fixed. Capture the exact failing command + output.
- Minimize — strip the repro to the smallest input / path that still fails. The minimal case usually names the cause.
- Hypothesize — state ONE falsifiable hypothesis ("X is null because Y returns early when Z"), not a vibe — a claim a check can disprove.
- Instrument — add the cheapest probe (a log, an assert, a breakpoint) that confirms or kills the hypothesis. Let evidence decide, not intuition. Killed → back to step 3.
- Fix the cause, not the symptom. A narrow patch that hides the symptom while the cause remains is a stopgap — label it as one if you must ship it.
- Regression-test — write a test that fails before the fix and passes after, so the bug can't silently return.
Discipline
- Verify against the REAL system (a real query / real run), never inferred from code alone.
- One hypothesis at a time; record what you ruled out.
- "Looks fixed" is not fixed — the regression test (red → green) is the proof.
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 · 36 lines · 77 tokens per session scan A b4a1f3c65cee
diagnose is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 408 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
javascriptcore-garbage-collector
JSC GC reference for Bun. Use for use-after-free, JS object leaks, "collected too early", or when touching WriteBarrier, visitChildren, visitAdditionalChildren, JSRef, JSC::Strong/Weak, hasPendingActivity, ensureStillAlive, addOpaqueRoot, reportExtraMemoryAllocated, IsoSubspace, HeapAnalyzer, finalize.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Builds a red-capable feedback loop and runs it before hypothesising — complements static code review (which finds bugs by reading) by running actual repros. Use when the user says 'diagnose'/'debug this', or reports something broken/throwing/failing/slow.
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, or behaviour does not match expectations. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the reproduction and regression steps follow the same red-green discipline as…
fix-bug
Run the Fix Validation pipeline to investigate, fix, and validate a bug. Ensures deterministic pipeline execution with IssueAnalyzer, FixWriter, TestWriter (conditional), TestAudit (conditional), and FixValidator stages.
debugging-workflows
Systematic troubleshooting for Falcon Foundry CLI errors, manifest validation failures, deploy failures, artifact runtime errors, and development server issues. TRIGGER when user encounters CLI errors, foundry ui run not working, deploy failures, authentication issues, function execution failures, "debug my function"…
ccc-systematic-debugging
Root-cause debugging via the Iron Law: no fix without confirmed root cause. Reproduce → hypothesize → verify → fix. Use when investigating bugs, test failures, or…