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 ai-driven-dev/framework --skill 08-debuggit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/08-debug)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/08-debug"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/08-debug/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/ai-driven-dev/framework/08-debug"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/08-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00052 | $0.00380 |
| Opus 5.5 | $0.00021 | $0.00152 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
08-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 3d 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
Skill: debug
Diagnose and fix issues through structured hypothesis validation, root-cause analysis, and a test-driven fix.
Actions
| # | Action | When to use |
|---|---|---|
| 01 | reproduce |
A known bug must be fixed end to end: reproduce, test-driven fix, branch, PR |
| 02 | debug |
Root cause unknown: enumerate hypotheses, validate each, confirm the cause |
| 03 | reflect-issue |
Stuck or prior fixes failed: reopen the search space, instrument logs first |
Pick the one action matching the intent; never default to 01. Triggers like "reproduce and fix" route to 01, "why does this happen" to 02, "I'm stuck" or "previous fixes didn't work" to 03. Ask one question when the intent is ambiguous. Before running an action, read its file in actions/, not only the table or assets.
Transversal rules
- One action per run: follow only the matching action file.
- Scope each fix to its bug: never bundle drive-by refactors.
- Confirm the root cause before fixing; the diagnostic actions stop at a confirmed cause.
Assets
assets/task-template.md: the per-hypothesis tracking file the debug action fills.
References
references/mermaid-conventions.md: the project's Mermaid conventions for the action-path flowchart.
What ships with it
5 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.
- 3d ago Changed · -1 lines afc8699c7a13
- 1mo ago First seen · 35 lines · 52 tokens per session scan A e00fa9e06a77
08-debug is a skill published in the GitHub repository ai-driven-dev/framework (522 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 380 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
bugfix-quick
Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
test-driven-development
Test-driven development discipline — write a failing test, implement the minimum to pass, then refactor. Use when adding a feature or fixing a bug where correctness matters.
tdd-strict
Use when high-assurance reliability is required (Bug fixes, Critical Features, Quality Hardening).