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/shennawardana23/skillme/debugnpx skills add shennawardana23/skillme --skill debuggit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/debug)<a href="https://agentmods.dev/skills/shennawardana23/skillme/debug"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/debug.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01156 |
| Opus 5 | $0.00047 | $0.00578 |
| Sonnet 5 | $0.00019 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug
Iron law
Do not guess. Do not apply a fix until you understand the root cause. Every fix must follow from evidence. "It might be X" is not sufficient — "evidence Y proves it is X" is.
Phase 1: reproduce
Establish a minimal reproduction before doing anything else:
- What exact input or action triggers the issue?
- What is the expected outcome? What is the actual outcome (exact error message, full stack trace)?
- Is it deterministic or intermittent?
- When did it start? What changed?
If you cannot reproduce it, you cannot fix it with confidence.
Phase 2: isolate
Narrow down the location:
- Binary search — which layer does the failure originate in?
- Remove variables — disable features, mock dependencies one at a time.
- Check inputs — is the problem in the data, not the code?
- Check environment — does it fail in prod but not dev, and why specifically?
For Go: check whether go test -race reveals it; add log.Printf("[DEBUG] state=%v", state) at layer boundaries; use dlv (Delve) for interactive stepping when a print-based binary search stalls.
Phase 3: diagnose
Identify the root cause with evidence: trace the execution path from input to failure; check every assumption (types, nil-ness, ordering, timing); for panics, read the stack trace top-to-bottom — the root cause is usually the deepest frame, not the one at the top where the panic surfaced.
Phase 4: fix
- Fix the root cause, not a symptom.
- Write a test that would have caught this bug — it should fail without the fix and pass with it.
- Check whether the same bug pattern exists in similar code elsewhere in the codebase.
- Update documentation if the behavior was wrong but previously undocumented as correct.
Common Go patterns
| Symptom | Likely cause | Check |
|---|---|---|
| nil pointer dereference | Unguarded pointer use | Add a nil check before dereference |
| goroutine leak | Missing stop signal | Add a context.Context or done channel |
| data race | Concurrent map/slice mutation | Add a mutex, or use sync.Map |
context deadline exceeded |
Missing timeout propagation | Pass ctx into every blocking call on the path |
| unexpected log output | Wrong logger instance | Check which logger got wired at construction |
| test flakiness | Time-dependent assertion | Use an eventually/poll pattern instead of a fixed sleep |
What ships with it
5 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.
- 5d ago First seen · 92 lines · 94 tokens per session scan A d88f133777af
debug is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,156 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
coding-protocol
Risk-scaled repo execution and code-evidence protocol. Skip architecture-only work, explanation, contract-preserving prose, and status. Use for contract changes, debugging, code review, implementation plans, and Git mutation; mixed tasks: only those parts.
fix-bug
Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw stack trace, error message, code pointer (file:line), screen recording, Linear ticket URL, or free-text symptom. Classifies the input, triages complexity (Phase 0.5) to pick between a fast lane and a full…
holistic-analysis
Forces a full holistic re-analysis when a fix or refactor isn't working. Instead of continuing to patch in isolation, this skill triggers a structured step-back analysis that traces the entire execution path end-to-end — from entry point to exit — analyzing each block, every contract boundary, and the full data flow.…
ci-auto-fix
Diagnoses a failed CI check, classifies it with an explicit verdict (code-bug | workflow-bug | dep-bug | env-bug | flaky | unsure), confidence-gates the fix (>=90 auto, 80-89 ask, <80 escalate), applies it, pushes, and iteratively verifies until CI passes — reverting the last commit if a brand-new failure appears.…
playwright-trace-analyzer
Analyzes Playwright E2E trace.zip archives (and bare trace JSONL when unpacked). Extracts the action timeline, network waterfall, console errors, and DOM-snapshot anchors, then identifies the highest-impact problems (flaky waits, slow selectors, network bottlenecks, hung actions, unhandled console errors, navigation…