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/epicsagas/epic-harness/debugnpx skills add epicsagas/epic-harness --skill debuggit clone --depth 1 https://github.com/epicsagas/epic-harnessWhat 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 | $0.00026 | $0.01045 |
| Opus 5 | $0.00013 | $0.00522 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
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 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.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug — Systematic Debugging
Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Symptom fixes are whack-a-mole debugging.
Process
0. Recall
- Query the knowledge graph:
epic mem search "ERROR_MESSAGE_OR_FILE"for the error message or file name - Check if a
resolutionorpatternnode exists for this error category - If a past resolution exists, apply it directly instead of re-debugging from scratch
Why: Past resolutions save 10-30 minutes of re-investigation. The knowledge graph exists so you don't repeat work.
1. Observe
- Read the full error message and stack trace
- Identify: What was expected? What actually happened?
- Note the exact file, line, and function
Why: Precise observation prevents misdiagnosis. Most debug loops start from skimming the error instead of reading it fully.
2. Hypothesize
Form 2-3 possible causes. Rank by likelihood.
Why: Ranked hypotheses prevent random code changes. Even a wrong hypothesis narrows the search space.
3. Isolate
- Narrow the scope: Binary search through recent changes
- Reproduce minimally: Smallest input that triggers the error
- Check assumptions: Print/log intermediate values
- Bisect:
git log --oneline -10— when did it last work?
Why: Isolation proves the cause before you touch any code. Without it, you're guessing.
4. Fix
- Fix the root cause, not the symptom
- If the fix is a workaround, add a TODO with explanation
Why: Root cause fixes are permanent. Symptom patches rot and hide the real bug.
5. Verify
- Run the failing test — must pass now
- Run the full test suite — no regressions
- If this was a bug, the regression test stays
Why: A passing fix without verification is wishful thinking. The full suite catches side effects.
6. Record
- If the fix involved 3+ debug steps, record a
resolutionnode viaepic mem add --title "..." --type resolution --body "..." - Include: error category, root cause, solution approach
- This enables future sessions to skip re-debugging the same class of issues
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 · 96 lines · 26 tokens per session scan A 6e3806ead344
debug is a skill published in the GitHub repository epicsagas/epic-harness (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,045 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.