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/bobbyjohnstx/tinycode/debugnpx skills add bobbyjohnstx/tinycode --skill debuggit clone --depth 1 https://github.com/bobbyjohnstx/tinycodeWhat 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 | $0.00041 | $0.00664 |
| Opus 5 | $0.00020 | $0.00332 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug
Use this skill when a specific thing is broken and you need to find the root cause fast.
When to Use
Use this skill when:
- The user says "debug", "why is this failing", "what broke", "X errors at runtime", or "this isn't working"
- A command, test, or hook is producing an error or unexpected output
- Session or orchestration behavior diverges from expectation in a reproducible way
- The user wants a diagnosis and next-step recommendation, not a broad investigation
When Not to Use
- The root cause is genuinely ambiguous with two or more competing explanations that need ranking — use
trace - The task is to confirm a fix works, not to find the cause — use
verify - The user wants broad cleanup or refactoring — use
ai-slop-cleanerorcode-reviewer - The user already knows the cause and wants it implemented — use
executor
Examples
Good: "The pre-commit hook fired but didn't block the commit — debug why" → Inspect hook output, reproduce with a test commit, identify the misconfigured condition.
Bad: "Why is auth slow sometimes but not always? Could be the DB, the cache, or a race condition"
→ That needs competing hypotheses ranked with evidence. Use trace.
Bad: "Verify the auth fix worked"
→ Use verify.
Goal
Find the real failure signal quickly and explain the next corrective step.
Workflow
- Read the user's issue description carefully.
- Inspect the most relevant local evidence first:
- failing tests or commands
- logs and traces
- relevant state or config files
- Attempt a narrow reproduction. If reproduction is not possible, state explicitly why and what evidence substitutes for it — do not proceed to a hypothesis without either a reproduction or a stated substitute.
- Distinguish symptoms from root cause.
- Recommend the smallest next fix or verification step.
Rules
- Prefer real evidence over guesses.
- When the issue involves orchestration, hooks, or agent flow, inspect logs, hook output, and config files first.
- If the issue is actually a product/runtime bug rather than app code, say so plainly.
- Do not prescribe broad rewrites before isolating the failure.
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 · 65 lines · 41 tokens per session scan A c68c24fada5b
debug is a skill published in the GitHub repository bobbyjohnstx/tinycode (11 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 664 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
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
archon-cli
Drive Archon through its CLI: run AI workflows on a repo, manage those runs (inspect, approve, reject, cancel, resume), set up Archon or change its config, author new workflows, and improve workflow prompts. Use when the user says "use archon", "run archon", "archon workflow", "fix issue #N with archon", "have archon…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
greet
A greeting skill for testing.