sdcorejs-debug

A structured debugging workflow for finding and fixing a specific software failure. It reproduces the problem, tests possible causes, applies the smallest safe fix and adds a focused regression test when practical.

In plain words
What is it for?
Use it for bugs, failing tests, flaky behavior, build or runtime errors, production-only failures and performance problems. It does not cover broad feature work or release and pull-request tasks.
Why use it?
It replaces guesswork and speculative changes with evidence about the actual cause. It also checks that the original failure and nearby behavior still work after the fix.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sdcorejs/sdcorejs-agent/sdcorejs-debug
Any agent
npx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-debug
Clone the repo
git clone --depth 1 https://github.com/sdcorejs/sdcorejs-agent

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,114 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.05114
Opus 5 $0.00037 $0.02557
Sonnet 5 $0.00015 $0.01023
Haiku 4.5 $0.00007 $0.00511

Measured yesterday against content hash 5db56cb94fdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdcorejs-debug 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 yesterday.

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.

.claude/skills/sdcorejs-debug/SKILL.md · 473 lines

How it starts

The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug - Evidence-Driven Root-Cause Workflow

Purpose

sdcorejs-debug owns safe root-cause analysis for concrete failures:

  • reproduce locally or evidence-confirm the bug;
  • isolate the smallest failing case;
  • classify debug_mode, bug_class, stack_profile, repro_status, and environment;
  • form and falsify hypotheses with a visible Hypothesis Ledger;
  • add temporary diagnostic instrumentation only when needed and track it;
  • apply the smallest safe fix for the confirmed root cause;
  • add or update a focused regression test when feasible;
  • verify the original repro and regression surface;
  • hand off to sdcorejs-ship before any commit, PR, changelog, or release flow.

It does not own broad feature implementation, unrelated test-plan generation, large new test suites, new test infrastructure, speculative fixes, direct Git artifacts, destructive production reproduction, or weakening tests to get a green result.

Shared Protocols

Read _refs/shared/runtime-protocols.md and load only the references needed by the current failure.

After the shared protocols and before edits, read these debugging refs:

  • _refs/shared/debugging-discipline.md
  • _refs/shared/debug-command-discovery.md
  • _refs/shared/debug-environment-guard.md
  • _refs/shared/debug-context.md
  • _refs/shared/debug-contract.mjs

The executable debug contract consumes the central registry and stable artifact/repository identity. It binds the failing implementation, semantic owner repository/module, execution host, test evidence, environment fingerprint, approved plan step, source fingerprint, and per-repository source revision map. Validate it before any write handoff.

Routing Boundary

Use sdcorejs-debug for root-cause analysis and fixing bugs, including failing tests when the user asks to debug, fix, investigate, resolve, or find root cause.

Correct routing:

  • "debug this failing test", "fix this failing Jest test", "root-cause this test failure", "investigate flaky test" -> sdcorejs-debug.
  • "write tests for X", "add unit tests", "run the test suite", "create UAT cases", "what should be tested?" -> sdcorejs-test.
  • sdcorejs-test may do read-only failing-output triage only when the user asks to explain, classify, or summarize output without changes.
  • When failing output implies a production bug or needs source changes, sdcorejs-test hands off to sdcorejs-debug with test_context, test_evidence, and the smallest failing command.
  • Preserve test_status, case/run IDs, environment/persona references, and redaction state. Carry ui_capture_context and artifact_context by reference/classification without attaching raw state, traces, or images. Start from the smallest reproduction and command; do not broaden the suite until the hypothesis needs it.
  • sdcorejs-debug may add or update a small focused regression test during a bug fix when the existing runner and test style are clear. Large suites, new infrastructure, multiple test levels, complex UAT/e2e coverage, dependency installs, or browser binary installs belong to sdcorejs-test.

Read the full file on GitHub · 473 lines

Changes

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.

  1. yesterday First seen · 473 lines · 74 tokens per session scan A 5db56cb94fdb

Subscribe to this mod's changes

sdcorejs-debug is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 74 tokens to every session and 5,114 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.

Related

Other skills, from other repositories

planning-with-files-ar

تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…

OthmanAdi/planning-with-files · 189 tokens

kl-consistency-test

Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…

sgl-project/sglang · 108 tokens

i18n-localization

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

vudovn/ag-kit · 27 tokens

dsh-web-documentation

Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.

zhu1090093659/dsh-web · 34 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens

indication-dossier

Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.

companion-inc/feynman · 43 tokens