{"slug":"repo-debugging-ledger","title":"repo-debugging-ledger","summary":"Debug repositories with a hypothesis ledger, checked locations, and loop-breaking discipline. Use when tests fail, CI fails, behavior regresses, local tooling errors, flaky bugs appear, or an investigation risks repeated searches, repeated commands, circular hypotheses, or unveri","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-10-20T16:45:04.383118Z","repo":{"url":"https://github.com/markoblogo/abvx-agent-skills","stars":16,"forks":0,"license":"MIT","updatedAt":"2026-10-28T20:47:43Z"},"bodyHtml":"<hr>\n<h2>name: repo-debugging-ledger\ndescription: Debug repositories with a hypothesis ledger, checked locations, and loop-breaking discipline. Use when tests fail, CI fails, behavior regresses, local tooling errors, flaky bugs appear, or an investigation risks repeated searches, repeated commands, circular hypotheses, or unverified fixes.\nlicense: MIT\nmetadata:\nabvx_status: experimental\nabvx_origin: original</h2>\n<h1>Repo Debugging Ledger</h1>\n<p>Use this skill as a lightweight overlay on normal debugging. Its job is to prevent loops and untested assumptions.</p>\n<h2>Start With A Repro Signal</h2>\n<p>Create the smallest useful pass/fail loop:</p>\n<ul>\n<li>unit/integration test,</li>\n<li>CLI command,</li>\n<li>HTTP request,</li>\n<li>browser script,</li>\n<li>fixture replay,</li>\n<li>log assertion,</li>\n<li>repeated flake trigger.</li>\n</ul>\n<p>If no loop exists, state the best available signal and what artifact would make it deterministic.</p>\n<h2>Hypothesis Ledger</h2>\n<p>Before editing, write or mentally maintain 3-5 ranked hypotheses:</p>\n<pre><code>H1:\nPrediction:\nProbe:\nResult:\nStatus: open / supported / falsified\n</code></pre>\n<p>Probe one variable at a time. Prefer evidence that distinguishes between hypotheses.</p>\n<h2>Checked-Location Ledger</h2>\n<p>Track what has already been inspected:</p>\n<pre><code>Checked:\n- file/function/command:\n  evidence:\n  conclusion:\n</code></pre>\n<p>Do not reopen the same file, rerun the same broad search, or repeat the same command unless a phase change makes it newly relevant: new failing signal, new stack trace, changed code, or a narrowed hypothesis.</p>\n<h2>Search And Instrumentation</h2>\n<ul>\n<li>Use <code>rg</code> and targeted file reads first.</li>\n<li>Search for exact symbols, error text, config keys, route names, and call sites before broad terms.</li>\n<li>Tag temporary logs with a unique marker such as <code>[DEBUG-7b3c]</code>.</li>\n<li>Remove temporary instrumentation before finalizing.</li>\n<li>If a likely area is exhausted, broaden to a different subsystem instead of cycling through the same files.</li>\n</ul>\n<h2>Fix Discipline</h2>\n<ul>\n<li>Add or identify a regression check before the fix when a reasonable seam exists.</li>\n<li>Keep the fix scoped to the supported hypothesis.</li>\n<li>Re-run the original repro signal after the fix.</li>\n<li>Run the project’s normal checks before finalizing, or explain the blocker.</li>\n</ul>\n<h2>Final Report</h2>\n<p>Include:</p>\n<ul>\n<li>root cause or best-supported cause,</li>\n<li>files changed,</li>\n<li>verification run,</li>\n<li>residual risks or missing test seam.</li>\n</ul>\n","files":[{"path":"agents/openai.yaml","sizeBytes":213,"isText":true},{"path":"SKILL_CARD.md","sizeBytes":1278,"isText":true},{"path":"SKILL.md","sizeBytes":2302,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-10-20T16:46:55.798428Z","sha256":"0B96B02132418B377776B5A95AE9A48220823F75C3A3A28C653F55267A6BFA70","sizeBytes":2315},"review":null,"source":{"repositoryUrl":"https://github.com/markoblogo/abvx-agent-skills","path":"skills/repo-debugging-ledger","license":"MIT","commit":"d4af8c3a5596ed055f5be5bbbd4c36b37d535530","subtreeSha":"F885B07C29E894495C7BF79F4287FE577B916C88E8BDA430B6C7579D73244A7D","lastSyncedAt":"2026-11-06T21:46:00.926584Z"},"reviewedAt":"2026-10-20T16:50:00.197415Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/markoblogo/abvx-agent-skills/tree/main/skills/repo-debugging-ledger"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install markoblogo-abvx-agent-skills@llmmart"},{"target":"git","command":"git clone https://github.com/markoblogo/abvx-agent-skills.git"}]}