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/getkimchi/kimchi/dap-debuggingnpx skills add getkimchi/kimchi --skill dap-debugginggit clone --depth 1 https://github.com/getkimchi/kimchiWhat 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 | $0.00037 | $0.02290 |
| Opus 5 | $0.00018 | $0.01145 |
| Sonnet 5 | $0.00007 | $0.00458 |
| Haiku 4.5 | $0.00004 | $0.00229 |
Grade A, and why
dap-debugging 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 3d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging with DAP Tools
Use this skill when you need runtime state — a value at a line, the exception that actually threw, which code path ran — and reading the source no longer answers the question.
Per-language launch config, source mapping, and expression syntax rules live
in reference files alongside this skill. Load the one matching your debuggee
before launching:
skill_view name="dap-debugging" file_path="references/go.md",
references/python.md, references/typescript.md, or
references/native.md.
The debugging loop
Debugging is a search: you are locating the first place observable state diverges from intended state. Each iteration narrows the search.
- Reproduce and name the symptom. Run the program normally first
(
bash). Write down the visible wrong thing: wrong output, exception, hang. The symptom anchors every breakpoint you set. - State your one-line hypothesis. "The cache returns a stale entry after eviction." One line, about data. If you cannot, read more code — debugging without a hypothesis is random walking.
- Probe the boundary where the symptom appears. Breakpoint at the observable wrong behavior (see placement rules below), inspect state. Ask: does it match expectations here?
- Move backward along the data flow. State is wrong at your probe → the corruption happened earlier. Find where the bad value was written (assignment site, mutation, argument pass) and probe there. Repeat until you reach a probe where state is correct — the divergence is between the last correct and first incorrect probe.
- Minimize the step distance. Steps between your last-correct and
first-wrong probes may still be large. Step (
step_over/step_in) through that window while re-evaluating the suspect expression. The statement where the expression flips from right to wrong is usually the bug — or one line away from it. - Fix, then verify at the same breakpoint. Re-run to the same probe with the fix and confirm state is now correct. Do not skip the verification pass.
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.
- 3d ago First seen · 187 lines · 37 tokens per session scan A df5507c2b220
dap-debugging is a skill published in the GitHub repository getkimchi/kimchi (2,216 stars, last pushed 4d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,290 once invoked, about $0.0002 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
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…