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 silvioventre/lovable-skills --skill debuggit clone --depth 1 https://github.com/silvioventre/lovable-skillsWrote 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/silvioventre/lovable-skills/debug)<a href="https://agentmods.dev/skills/silvioventre/lovable-skills/debug"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/debug.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00168 | $0.01184 |
| Opus 5 | $0.00084 | $0.00592 |
| Sonnet 5 | $0.00034 | $0.00237 |
| Haiku 4.5 | $0.00017 | $0.00118 |
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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug
Find the root cause, then fix that. A change that makes the error message disappear without explaining why the error happened is not a fix — it relocates the bug.
Route the symptom
Read the user's description and any pasted error, then load the one playbook that owns it. Do not load more than one to start; the playbook will tell you if the trail leads elsewhere.
| Symptom | Playbook |
|---|---|
| Build fails, red error banner, syntax or type error | reference/build-and-preview.md |
| Blank page, white screen, nothing renders | reference/build-and-preview.md |
| Preview not found, sandbox stuck spinning up | reference/build-and-preview.md |
| "File exceeds the 10 MB per-file commit limit" | reference/build-and-preview.md |
| No error, but the app does the wrong thing | reference/behavior.md |
| A component or whole section vanished | reference/behavior.md |
| Worked before the last change, broken now | reference/behavior.md |
| State stale, UI not updating after an action | reference/behavior.md |
| Data will not load, empty list, wrong rows | reference/backend.md |
| Edge function failing or not deploying | reference/backend.md |
| "Permission denied", RLS, user sees nothing or too much | reference/backend.md |
| Login, session, or role check misbehaving | reference/backend.md |
| Same error keeps returning, or a new one each fix | reference/loops.md |
| Two or more fix attempts with no progress | reference/loops.md |
| The project feels too tangled to repair | reference/loops.md |
| A monitoring check reported a finding | reference/triage.md |
What ships with it
7 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.
- 7d ago First seen · 60 lines · 168 tokens per session scan A e72f7d3610d5
debug is a skill published in the GitHub repository silvioventre/lovable-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 168 tokens to every session and 1,184 once invoked, about $0.0008 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 skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
hotfix-triage
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes.