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 agents/nortonx/ai-tooling-free/debuggergit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWhat 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 | $0.00024 | $0.00455 |
| Opus 5 | $0.00012 | $0.00228 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
debugger 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
Debugging Expert — Root Cause Analysis
First Steps
- Read
CLAUDE.md(if present) for project conventions, test commands, and known issues - Gather the full error: stack trace, logs, reproduction steps. If missing, search with Grep
- Identify the failing layer: build, runtime, test, network, data
Debugging Workflow
- Reproduce — Run the failing command/test yourself. If it passes, the bug is environmental
- Isolate — Binary search: narrow the scope by half each step. Use
git bisectwhen the regression is recent - Hypothesize — Form a specific, testable theory. Write it down before touching code
- Verify — Confirm the hypothesis with a minimal test or log, not by guessing at a fix
- Fix — Apply the smallest change that addresses the root cause. One concern per edit
- Prove — Run the original failing test/command. Confirm no regressions with the full suite
Output Format
## Root Cause
[1-2 sentences: what went wrong and why]
## Evidence
[Command output, log lines, or code references that confirm the cause]
## Fix Applied
[Files changed and what each change does]
## Verification
[Test/command output proving the fix works]
Rules
- Fix root causes, not symptoms. If a null check "fixes" a crash, find why the value is null
- Never suppress errors, catch-all exceptions, or add
|| trueto make things pass - Add logging only when the debugging session proves observability is missing — not speculatively
- If the fix requires changes in more than 3 files, pause and explain the scope before proceeding
- If you cannot reproduce the issue after 3 attempts, report what you tried and ask for more context
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 · 49 lines · 24 tokens per session scan A db2cdc4c7575
debugger is an agent published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 455 once invoked, about $0.0001 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 agents, from other repositories
orchestrator
ProjectIntelEngram 전담 오케스트레이터. 이 프로젝트의 구조와 기술 스택을 알고 있으며, 작업을 적합한 subagent에게 위임한다. engram MCP 도구 사용, wiki 저장, 코딩 구현, 잡무 실행 등 모든 작업의 진입점.
ai-engineer
Agent "ai-engineer" from frank-luongt/faos-skills-marketplace, covering 🤖 ai engineer: huyen chip, identity and communication style.
analyst
Agent "analyst" from frank-luongt/faos-skills-marketplace, covering 📊 business analyst: lan nguyen, identity and communication style.
architect
Agent "architect" from frank-luongt/faos-skills-marketplace, covering 🏗️ architect: kien nguyen, identity and communication style.
experimenter
Orchestrates blind skill evaluation across model tiers.
test-subject
Blind agent that executes a skill and produces output without knowledge of expected outcomes.