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 DBvc/agent-skill-control-theory --skill frontend-debuggit clone --depth 1 https://github.com/DBvc/agent-skill-control-theoryWrote 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/dbvc/agent-skill-control-theory/frontend-debug)<a href="https://agentmods.dev/skills/dbvc/agent-skill-control-theory/frontend-debug"><img src="https://agentmods.dev/badge/skills/dbvc/agent-skill-control-theory/frontend-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/dbvc/agent-skill-control-theory/frontend-debug"><img src="https://agentmods.dev/badge/skills/dbvc/agent-skill-control-theory/frontend-debug.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00975 |
| Opus 5.5 | $0.00020 | $0.00390 |
| Sonnet 5.5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
frontend-debug scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Prefer existing test commands, focused tests, Playwright or browser checks, storybook states, curl/API fixtures, or small reproduction scripts. How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Debug
Use this skill to diagnose and fix active frontend failures with evidence, feedback loops, and completion proof.
This is a synthetic example built with Agent Skill Control Theory. It is intentionally not tied to any specific framework.
Purpose
The goal is to move from observed broken behavior to a verified fix.
The goal is not to redesign the feature, review unrelated code, or make broad quality improvements.
Mode selection
Choose the smallest sufficient mode.
quick: small, reproducible bug with obvious scope.standard: normal runtime, rendering, state, or interaction bug.deep: flaky behavior, cross-browser issue, production regression, data loss, security-sensitive UI, or repeated failed attempts.clarification: required reproduction details or access are missing.safety_redirect: the request asks for unsafe, deceptive, or unauthorized behavior.
Required inputs
Identify:
- observed symptom;
- expected behavior;
- reproduction path or missing reproduction information;
- environment if relevant;
- current files, diff, logs, test output, or screenshots available;
- validation commands available in the repository.
If the reproduction path is missing but can be discovered by inspecting tests, routes, stories, logs, or code, inspect before asking the user.
Hard gates
Do not edit code until one of these exists:
- a reproducible pass/fail signal;
- a failing test;
- a browser or interaction script;
- a minimal manual reproduction path;
- a clear log or trace that maps to the symptom.
Do not propose a fix until you can state a falsifiable root-cause hypothesis.
Do not claim success unless validation evidence supports the claim.
Workflow
-
Symptom inventory
- Restate the observed behavior and expected behavior.
- List all known symptoms.
- Note uncertainty and missing inputs.
-
Feedback loop
- Establish the fastest reliable pass/fail signal.
- Prefer existing test commands, focused tests, Playwright or browser checks, storybook states, curl/API fixtures, or small reproduction scripts.
- If no automated loop is available, document the manual reproduction path.
What ships with it
3 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.
- 1mo ago First seen · 154 lines · 51 tokens per session scan A 43ed2207cfc6
frontend-debug is a skill published in the GitHub repository DBvc/agent-skill-control-theory (2 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 975 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.