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 skills add kardebadas/claude-plugin --skill bug-investigategit clone --depth 1 https://github.com/kardebadas/claude-pluginWrote 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/kardebadas/claude-plugin/bug-investigate)<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/bug-investigate"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/bug-investigate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/bug-investigate"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/bug-investigate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.00928 |
| Opus 5.5 | $0.00033 | $0.00371 |
| Sonnet 5.5 | $0.00017 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
bug-investigate 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Investigate
Overview
Finds the root cause of a bug and reports it. That is the whole job.
No plan, no fix, no edits. Knowing what is wrong is often the thing that is actually needed — because the fix is obvious once you know, because the decision about whether to fix is someone else's, or because the answer changes what gets built rather than what gets patched.
This is the same investigation superb:bug-fix runs as its first step. The
difference is where it stops. If you already know you want the bug fixed end to
end, use superb:bug-fix and let it carry the result into a plan.
Step 0 — Assemble the report
The investigator needs five things, and the invocation argument usually supplies one or two:
| Field | Example |
|---|---|
| Symptom | "uploads over ~5MB fail silently" |
| Reproduction | the steps, or unknown |
| Error text | stack trace, log line, or none surfaced |
| Affected surface | endpoint, screen, command, job |
| Last known good | a date, a release, a commit, or never worked |
Ask for whatever is missing in one batched question, not five. unknown is a
fine answer and belongs in the brief; a silently empty field is not, because the
investigator will fill it with a guess.
Step 1 — Investigate
Take the first branch that applies:
| Condition | What to do |
|---|---|
A subagent mechanism, and superb:bug-investigator is in your available agent types |
Dispatch superb:bug-investigator with the Step 0 report. |
| A subagent mechanism, but that agent is not listed | Dispatch a general subagent, briefed with the text between the SHARED BRIEF markers in ../bug-fix/references/investigator.md. |
| No subagent mechanism | Follow that same bracketed brief yourself, inline, including its "modify no files" rule. |
Name the agent superb:bug-investigator, with the prefix. A bare
bug-investigator resolves to whatever personal agent happens to exist.
Do not substitute superpowers:systematic-debugging. Its four phases run
through hypothesis-testing and implementation, so it would fix the bug — which
is the one thing this skill is for not doing.
What ships with it
1 file 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.
- 1mo ago First seen · 80 lines · 83 tokens per session scan A 780d454eba1f
bug-investigate is a skill published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 22d ago), licensed Apache-2.0. It adds 83 tokens to every session and 928 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
diagnose-project
Diagnose .NET SDK, restore, build, test, package, target framework, F# compile-order, C# analyzer, and project-reference failures with concrete next checks.
xcode-build-run-workflow
Guide build, run, preview-adjacent, workspace-inspection, diagnostics, toolchain, and guarded mutation work in existing Xcode-managed projects and workspaces. Use when Xcode-aware execution is needed and the task is primarily about build, run, or project-integrity work rather than testing.
safari-mcp-workflow
Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
xcode-debugger-mcp-workflow
Diagnose a running Apple app through Xcode’s active LLDB debugging session and assess the experimental Xcode 27 lldb-mcp executable. Use when setting breakpoints, inspecting frames or variables, issuing LLDB commands, or distinguishing a usable Xcode debugger session from an unavailable standalone debugger MCP server.
xcode-device-hub-workflow
Manage and validate simulated and physical Apple devices through Xcode Device Hub. Use when selecting or inspecting run destinations, interacting with an app, changing simulated-device environment settings, capturing screenshots or videos, pairing a device, or collecting diagnostics.
ios-runtime-forensics-workflow
Capture and interpret reproducible iOS Simulator performance and memory evidence. Use when an iOS issue needs ETTrace/symbolication, a memgraph, leak ownership traces, or before/after runtime proof rather than a code-only guess.