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/bigduu/bamboo-agent/debugnpx skills add bigduu/Bamboo-agent --skill debuggit clone --depth 1 https://github.com/bigduu/Bamboo-agentWhat 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 | $0.00064 | $0.00263 |
| Opus 5 | $0.00032 | $0.00131 |
| Sonnet 5 | $0.00013 | $0.00053 |
| Haiku 4.5 | $0.00006 | $0.00026 |
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.
What it actually says
Debug
Diagnose before changing code.
- Capture the exact symptom, expected behavior, environment, and smallest known trigger from the request and available artifacts.
- Reproduce the failure with the narrowest safe command. Establish whether it also occurs on the relevant clean baseline when that distinction matters.
- Form a small set of falsifiable hypotheses. Inspect logs, state transitions, call sites, and tests to eliminate alternatives.
- State the root cause only when evidence connects the trigger to the symptom; keep remaining hypotheses labeled as uncertain.
- Modify files only when the user asked for a fix. Make the smallest root-cause change and verify the reproducer first, then the affected suite.
Report the symptom, root cause or best-supported hypothesis, evidence, change status, verification, and remaining risk. Preserve these facts across context compaction. When a tool fails or permission is denied, try safe evidence sources already in scope and describe what remains unverified.
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.
- 2d ago First seen · 17 lines · 64 tokens per session scan A bdee08df9925
debug is a skill published in the GitHub repository bigduu/Bamboo-agent (16 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 263 once invoked, about $0.0003 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
harbor
Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.
data-analysis
Use this skill when the user asks to analyze data from CSV, JSON, Excel, or database exports — including exploring datasets, computing statistics, creating visualizations, finding patterns, cleaning data, or building dashboards. Trigger whenever the user provides a data file and wants insights, charts, or…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', '.docx', or requests to produce professional documents with headings, tables of contents, page numbers, or letterheads. Also use for extracting content from .docx…
image-gen
Use this skill when the user asks to create, edit, or manipulate images programmatically — including diagrams, charts, infographics, thumbnails, social media graphics, image processing (resize, crop, filter, watermark), or generating visual assets from data. Trigger when the output is a .png, .jpg, .svg, or .gif file.
Use this skill whenever the user wants to do anything with PDF files — reading, extracting text or tables, merging, splitting, rotating, creating new PDFs, adding watermarks, OCR on scanned documents, encrypting/decrypting, or filling forms. Trigger whenever a .pdf file is mentioned or needs to be produced.
pptx
Use this skill any time a .pptx file is involved — creating slide decks, reading or extracting content from presentations, editing existing slides, or converting between formats. Trigger whenever the user mentions 'deck', 'slides', 'presentation', or references a .pptx filename.