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/frane/vibesurfer/debug-failed-actionnpx skills add frane/vibesurfer --skill debug-failed-actiongit clone --depth 1 https://github.com/frane/vibesurferWrote 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/frane/vibesurfer/debug-failed-action)<a href="https://agentmods.dev/skills/frane/vibesurfer/debug-failed-action"><img src="https://agentmods.dev/badge/skills/frane/vibesurfer/debug-failed-action.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 | $0.00054 | $0.00482 |
| Opus 5 | $0.00027 | $0.00241 |
| Sonnet 5 | $0.00011 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
debug-failed-action 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 4d 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
debug-failed-action
When to use
You ran vs_act and one of:
- The next
vs_viewlooks identical to the previous one (no DOM change). - You got
! NOT_FOUND ref=Neven though the ref was in the most recent tree. - A button you clicked appears
disabled/aria-busy/pointer-events: nonein the DOM but not in the semantic tree. - A form submission completed in the UI but the underlying API call returned 4xx/5xx silently.
What it does
Runs three on-demand inspections in sequence against the page that owns the failed action:
vs_inspect console --since=<token> --level=error,warn— every console.error / console.warn / uncaught exception captured since the action's pre-token.vs_inspect network --since=<token> --status=4xx,5xx— every 4xx/5xx network response since the action's pre-token.vs_inspect performance— Web Vitals + heap + DOM-stat block.
The output is concatenated and sectioned by source, prefixed with one-line headers.
Arguments
token— thestate_tokenyou held before issuingvs_act. The skill uses it as--since=<token>for both console and network slices.page— thep_<id>fromvs_status. If omitted, the skill uses the only open page in the active session; if there are multiple, it errors and prompts.
Why this is the canonical use case
Failed-action debugging is the universal pain point with agent-driven browser automation. The semantic tree shows you what the page says it is; the inspection surface shows you what the page actually did in the second between your action and your re-read. If you don't reach for this skill in real failure cases, the M5.7 inspection surface didn't land.
What ships with it
1 file 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.
- 4d ago First seen · 36 lines · 54 tokens per session scan A c8c4fc5faabe
debug-failed-action is a skill published in the GitHub repository frane/vibesurfer (15 stars, last pushed 7d ago), licensed Apache-2.0. It adds 54 tokens to every session and 482 once invoked, about $0.0003 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.