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 agentmods add skills/int2t05/engineering-skills/debuggingnpx skills add int2t05/engineering-skills --skill debugginggit clone --depth 1 https://github.com/int2t05/engineering-skillsWhat 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 | $0.00105 | $0.01774 |
| Opus 5 | $0.00053 | $0.00887 |
| Sonnet 5 | $0.00021 | $0.00355 |
| Haiku 4.5 | $0.00011 | $0.00177 |
Grade A, and why
debugging scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Build a **tight feedback loop** that goes red on this bug. This is the skill — everything else is mechanical. If you have a tight pass/fail signal for _this_ bug, you will find the cause; if you don't, no amount of stari How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- Tests fail, the build breaks, or runtime behavior doesn't match expectations
- A bug report arrives or an error appears in logs/console
- Something worked before and stopped
- A performance regression needs diagnosing
- Before proposing a fix — discipline beats guessing
- Reading error output or logs to triage before building a full reproduction loop (see
references/log-triage.md) - Triggers on "debug", "bug", "test failure", "unexpected behavior", "调试", "排查 bug", "读日志", "排查错误日志"
Not for: performance optimization (use performance); profiling measured slowness (use performance). Production incidents where containment must precede diagnosis (use incident-response).
Steps
Stop the line. When anything unexpected happens, stop adding features. Preserve evidence (error output, logs, repro steps). Diagnose the root cause; resume only after verification passes. Don't push past a failing test or broken build — errors compound.
Redact every secret in command output, logs, and captured artifacts before showing them — write <REDACTED> in its place. Build loops against env vars so credentials stay in the environment. If redacted output isn't enough to diagnose, say so and ask the user.
1. Reproduce (go red)
Build a tight feedback loop that goes red on this bug. This is the skill — everything else is mechanical. If you have a tight pass/fail signal for this bug, you will find the cause; if you don't, no amount of staring at code will save you. Try in roughly this order: failing test → curl/HTTP script → CLI invocation with fixture → headless browser script → replay a captured trace → throwaway harness → property/fuzz loop → bisection harness → differential loop → HITL bash script (last resort, via references/hitl-loop-template.sh).
Tighten the loop: faster (cache setup, narrow scope), sharper signal (assert the specific symptom, not "didn't crash"), more deterministic (pin time, seed RNG, isolate filesystem).
Non-deterministic bugs: the goal is a higher reproduction rate, not a clean repro. Loop the trigger 100×, parallelise, inject sleeps, narrow timing windows. A 50%-flake bug is debuggable; 1% is not.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 90 lines · 0 tokens per session scan A 9dc7b4da3b6d
debugging is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 105 tokens to every session and 1,774 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…
production-engineering-workflows
End-to-end production engineering workflows that encode the complete software development lifecycle into repeatable, quality-gated agent commands. Covers everything from spec-driven ideation through planning, test-driven implementation, automated testing, rigorous code review, web performance auditing, code…
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
software-test-execution
Run scoped tests for a TDD slice, determine the appropriate test framework and command, and report structured pass/fail results. Use when tests need to be executed after writing, implementing, or refactoring code. Reads test metadata, discovers the test framework if needed, executes the scoped test command, parses…
nw-at-completeness-check
Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.
nw-canary
Canary skill for auto-injection detection.