Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/deep-debuggingWrote 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/nguyenthienthanh/aura-frog/deep-debugging)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/deep-debugging"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/deep-debugging/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/nguyenthienthanh/aura-frog/deep-debugging"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/deep-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 158 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 159 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 160 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00049 | $0.01459 |
| Opus 5.5 | $0.00020 | $0.00584 |
| Sonnet 5.5 | $0.00010 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
deep-debugging 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Deep Debugging
For bugs where bugfix-quick fails. Apply scientific method, not vibes.
Escalation path: bugfix-quick (< 15 min, clear cause) → deep-debugging (scientific method)
Uses: tree-of-thoughts skill for hypothesis trees, chain-of-verification for claim validation
When to Use vs. bugfix-quick
| Signal | Use |
|---|---|
| Stack trace points to clear line | bugfix-quick |
| Reproduces 100% of the time | bugfix-quick |
| Happens in known edge case | bugfix-quick |
| Intermittent / flaky | deep-debugging |
| Multiple plausible causes | deep-debugging |
| "Works on my machine" class | deep-debugging |
| Timing / race conditions | deep-debugging |
| Production-only, can't repro locally | deep-debugging |
The Protocol
Step 1 — Reproduce reliably
Cannot debug what you can't reproduce. Goals:
- Minimum reproduction case (strip all non-essential code)
- Document trigger conditions (env, timing, order of operations)
- If intermittent: repeat N times, calculate failure rate
If can't reproduce: STOP. You can't debug. Alternative: add observability (logging, metrics, traces) to production to catch the next occurrence. Don't guess.
Step 2 — Form a hypothesis tree (via tree-of-thoughts)
Don't jump to the first suspicion. Enumerate possibilities:
Root: Login fails intermittently in production
├── Branch A: Session store issue
│ ├── A1: Redis connection pool exhausted
│ ├── A2: Cookie domain mismatch
│ └── A3: Session expiry race condition
├── Branch B: Load balancer / infra
│ ├── B1: Sticky session misconfigured
│ └── B2: TLS termination timing
└── Branch C: Auth service
├── C1: JWT clock drift
└── C2: Rate limit hit
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 · 164 lines · 49 tokens per session scan A 54e578d3a150
deep-debugging is a skill published in the GitHub repository nguyenthienthanh/aura-frog (25 stars, last pushed 19d ago), licensed MIT. It adds 49 tokens to every session and 1,459 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
biome
Biome formatting and linting standards. Use when configuring Biome (biome.json) for fast formatting, linting, and sorting imports. NOT for Prettier or ESLint configuration. Do NOT trigger for generic formatting/linting tasks unless Biome is explicitly requested.
adversarial-performance
Multi-pass adversarial performance audit for entire repositories. Combines structured profiling (Agent A) with adversarial stress-testing critique (Agent B) through iterative passes. Optimize repo/backend performance, hot-paths, build size, and server throughput. Do NOT use for frontend page load metrics or Lighthouse…
autonomous-dev
Harness for autonomous software development. Use when fixing or remediating known issues (including security vulnerabilities). Enforces lifecycle through alignment gates (PROJECT.md), adversarial generator/evaluator agents, and autonomous orchestration of project issues. NOT for setting up standalone CI/CD pipelines.
debugger-coordinator
Use when debugging complex issues involving multiple modalities (frontend + backend, API + UI, terminal + browser). Coordinates Hermes Agent's built-in debugger, browser, terminal, and vision tools for systematic root-cause analysis.
gsd-debug
Systematic debugging with persistent state across context resets.
gsd-ns-review
quality gates | code review debug audit security eval ui.