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 lfyxhappy/lfcode --skill test-debuggergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/test-debugger)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/test-debugger"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/test-debugger/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/lfyxhappy/lfcode/test-debugger"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/test-debugger.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 | $0.00054 | $0.00345 |
| Opus 5 | $0.00027 | $0.00172 |
| Sonnet 5 | $0.00011 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
test-debugger 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.
What it actually says
Test Debugger
Diagnose failures from reproducible evidence and keep test intent intact.
Workflow
- Read repository instructions, package scripts, the failing test, its fixture setup, and recent relevant diffs.
- Record the exact package, command, runtime, and failure output. Run the smallest reproducible test first, then repeat only when checking flakiness.
- Classify the failure as assertion mismatch, setup/fixture problem, timing or concurrency issue, resource leak, dependency mismatch, or environment/tooling failure.
- Trace the failing code path and inspect actual inputs, outputs, logs, and cleanup. Do not guess from a stack frame alone.
- If a change is requested, make the smallest fix that preserves the test's behavioral contract. Add a regression case only when it captures a missing contract.
- Rerun the focused test, then the affected package checks when shared code or interfaces changed.
Boundaries
- Do not delete, weaken, skip, broaden, or rewrite a failing assertion merely to obtain a green run.
- Separate a diagnosis, a recommended fix, and an implemented fix in the report.
- Avoid flaky sleeps and mocks that hide the real failure. Redact secrets and machine-specific data from logs.
Completion check
Report the reproduction command, root cause or bounded hypothesis, changed files if any, and every verification command that passed or remains unavailable.
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 First seen · 28 lines · 54 tokens per session scan A aa70ec3b56fa
test-debugger is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 345 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
bug-fix
A structured bug-fixing workflow that takes a problem from reproduction and evidence-based cause finding through approval, implementation, testing, and cleanup.
mandu-mcp-verify
An automatic verification workflow for the Mandu project that runs after edits, generated files, or before a commit. It checks generated behavior, architecture rules, code quality, and project structure in parallel.
termcanvas-agent-sync-debugging
Diagnose TermCanvas agentmux nodes that fail to appear and terminal canvases that become janky, resize repeatedly, or show corrupted/unreadable xterm text as terminal count grows, plus duplicate terminal views created after a release relaunch. Use when a child agent is missing, restored terminals duplicate or move to…
repair-prevention-assessment
A completion gate for fixes and self-repair work. It creates a machine-checkable assessment that separates evidence a current issue is closed from evidence that the fix will remain effective.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
PR babysit (watch & drive to green)
Watch a pull request and delegate fixes until CI is green and reviews are addressed. Requires the GitHub MCP server or gh.