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 MarcZxc1/qwykz --skill deep-analysisgit clone --depth 1 https://github.com/MarcZxc1/qwykzWrote 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/marczxc1/qwykz/deep-analysis)<a href="https://agentmods.dev/skills/marczxc1/qwykz/deep-analysis"><img src="https://agentmods.dev/badge/skills/marczxc1/qwykz/deep-analysis/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/marczxc1/qwykz/deep-analysis"><img src="https://agentmods.dev/badge/skills/marczxc1/qwykz/deep-analysis.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 | $0.00067 | $0.00583 |
| Opus 5 | $0.00034 | $0.00292 |
| Sonnet 5 | $0.00013 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
deep-analysis 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 9d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep analysis
Use this skill when the user asks for a deep or comprehensive analysis. Treat the request as an investigation first; do not silently convert it into an implementation request.
Workflow
- Define the analysis scope from the request. Identify the exact project, files, systems, environments, and decision the user cares about. State reasonable assumptions briefly.
- Map the relevant surface area before forming conclusions. Inspect entry points, configuration, package manifests and lockfiles, generated or runtime artifacts, tests, CI/build scripts, and documentation. Search broadly with
rgand inspect targeted files in full enough context. - Trace behavior end to end. Follow inputs through prompts/configuration, code paths, templates, generated output, dependencies, and runtime/build consumers. Check both the intended path and important failure paths.
- Separate evidence from inference. For every important finding, record the concrete file, line, command output, test result, or reproducible behavior that supports it. Label assumptions, uncertainty, and gaps explicitly.
- Check contradictions and edge cases. Compare declarations against actual behavior, especially package versions, framework-specific dependencies, optional selections, defaults, generated files, platform differences, and CI behavior.
- Validate proportionally. Run the narrowest useful tests or builds, then expand to integration or matrix checks when the risk is cross-cutting. Do not claim validation that was not run; distinguish blocked checks from passing checks.
- Produce a decision-ready report before changing files: conclusion, findings ranked by severity, evidence, likely root cause, impact, confidence, unresolved questions, and recommended next steps. If the user also asked to fix something, make the smallest safe change after the analysis and verify it.
Reporting rules
- Lead with the conclusion, then supporting evidence.
- Use precise paths and line references where useful.
- Distinguish confirmed bugs from risks, design opinions, and missing evidence.
- Explain why a dependency or package is included, not merely that it exists.
- For generated projects, inspect the generated manifest and build output rather than trusting generator intent.
- Preserve unrelated working-tree changes.
- Never hide a failed, skipped, or unavailable check behind a general statement such as “it works”.
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.
- 9d ago First seen · 38 lines · 67 tokens per session scan A 9ff9cb47d423
deep-analysis is a skill published in the GitHub repository MarcZxc1/qwykz (5 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 583 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…