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/panda850819/verbs/debugnpx skills add panda850819/verbs --skill debuggit clone --depth 1 https://github.com/panda850819/verbsWhat 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 | $0.00074 | $0.00535 |
| Opus 5 | $0.00037 | $0.00267 |
| Sonnet 5 | $0.00015 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00053 |
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 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.
What it actually says
Debug
You already know how to debug. This skill is not the method. It overrides the momentum reflexes you get wrong and points you to lore you cannot derive.
Override
- Name the root cause before you edit. At
file:function:line, with the evidence. "A state issue" is not a root cause; "stale cache inuseUseratuser.ts:42, dep array missinguserId" is. Editing before you can say that sentence is the failure mode. - Diagnosis ends only on a red-capable command. Name one already-run deterministic, fast, agent-runnable command that can fail, and say you saw its output. "I understand the bug" is not done.
- Do not claim fixed until you ran it and looked. "Should work" is not evidence. Compile-only is not enough for UI / native / generated-artifact bugs: open it, and for generated output read the contents, not the source diff. Cannot run it here → say so and hand off the exact check.
- Before "fixed", grep the signature for siblings. One fix that ignores siblings leaves N-1 in the tree; the same shape usually hides elsewhere.
Lore (consult when the cause is not obvious)
lib/diagnosis.md — known bug classes (listener-owns-lifetime, O(N²)
accumulators, schema category-leak, and CLI archetypes: PATH drift, stdout/stderr contract, pipe
backpressure, cold-start), instrument-first-by-bug-class, bisect with worktree safety, and the
3-failed-hypotheses handoff template.
Recall first per @lib/learning-recall.md:
pull from the repo learning path configured by the host project, matching the symptom / bug class before
hypothesizing. A new reusable bug class emits a candidate using
lib/learning-format.md; a match emits a one-line seen again candidate. Never
write or update the learning store here. Persistence belongs to the host/project.
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.
- yesterday First seen · 40 lines · 74 tokens per session scan A 66ca58e2f645
debug is a skill published in the GitHub repository panda850819/verbs (5 stars, last pushed 9d ago), licensed MIT. It adds 74 tokens to every session and 535 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.
Other skills, from other repositories
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
markstream-vue2-cli
Integrate markstream-vue2 into a Vue 2 Vue CLI or Webpack 4 app. Use when Codex needs Webpack 4-friendly setup, CDN worker fallbacks for Mermaid or KaTeX, dist/index.css imports, Vue 2 composition-api shims, or code block choices limited to stream-diffs or plain .
markstream-svelte
Integrate the beta markstream-svelte package in Svelte 5 or SvelteKit apps. Use when Codex needs Svelte 5 runes, CSS and optional peers, smooth streaming, worker setup, renderer-local or scoped custom components, or SSR-safe boundaries. Svelte 4 is unsupported.
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…