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 pe-menezes/vibeflow --skill vibeflow-analyzegit clone --depth 1 https://github.com/pe-menezes/vibeflowWrote 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/pe-menezes/vibeflow/vibeflow-analyze)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/vibeflow-analyze"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/vibeflow-analyze/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/pe-menezes/vibeflow/vibeflow-analyze"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/vibeflow-analyze.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 | $0.00058 | $0.06662 |
| Opus 5.5 | $0.00023 | $0.02665 |
| Sonnet 5.5 | $0.00012 | $0.01332 |
| Haiku 4.5 | $0.00006 | $0.00666 |
Grade C, and why
vibeflow-analyze scanned grade C 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Remove the temp directory (`rm -rf <temp_dir>`) whether the merge succeeded or This is a copy
88% identical to analyze — 94 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibeflow: Analyze
Deep-analyze the current codebase. Discovers stack, architecture,
patterns, conventions, key components, and pitfalls. Creates curated
documentation in .vibeflow/ that persists and can be committed to git.
Supports incremental analysis: if .vibeflow/ already exists, detects
changes via git and updates only affected modules.
Usage: Invoke this skill from the project root. Pass --fresh as input to force a complete rebuild. Pass --scope <path> to deep-dive into a specific module/directory. Pass --interactive to validate and enrich patterns with human feedback before saving. Pass --satellite <url> to analyze a dependency repo and merge only used patterns. Pass --measure to run the full-suite and affected-tests commands once each and record their time; without it they are recorded but not run, because a project's suite can start containers, call services or take many minutes.
Language
Detect the language of the user's conversation context.
Write ALL output in that same language.
Technical terms in English are acceptable regardless of the detected language.
Section names in generated .vibeflow/ files may be in English (they are technical),
but all descriptive text, analyses, observations, and final user reports should be
in the detected language.
Perform a deep, adaptive analysis of this codebase. The goal is curated pattern documentation that every future spec, prompt pack, and audit uses to keep implementations on the project's real conventions.
Phase 0: Detect mode
Read .vibeflow/index.md directly by its path. Search, grep, and glob respect
.gitignore, so they miss the directory and report it as absent.
Then read the flags in the input (--fresh, --scope <path>, --interactive,
--satellite <url>, --measure) and check whether git is available here.
Decision tree:
--satellite <url>→ satellite mode (below); phases 1–5 don't run. Without an existing.vibeflow/index.md, stop: "Run the vibeflow-analyze skill first to establish project context, then use--satelliteto analyze a dependency repo."--scope <path>→ scoped mode (below); phases 1–5 don't run. Without an existing.vibeflow/index.md, stop: "Runanalyzefirst to establish project context, then use--scopeto deep-dive into specific modules."- No
.vibeflow/, or--freshpresent → full analysis, phases 1–5. .vibeflow/exists and no--fresh→ incremental analysis.--interactivecomposes with every mode: it adds Phase 3.5 before saving and changes nothing else about which phases run.--measurecomposes with every mode that writes the Tests and Pitfalls block: it makes the block due even when nothing else changed, so the commands are measured on an up-to-date project too (the block-only path below), and it runs the two test commands once (Tests and Pitfalls, in Phase 4).
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.
- 2d ago Changed · +46 lines 12aca8d445a7
- 1mo ago First seen · 545 lines · 58 tokens per session scan C 67446db5fd8a
vibeflow-analyze is a skill published in the GitHub repository pe-menezes/vibeflow (32 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 6,662 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 88% identical to analyze, differing in 94 lines, and is treated as a copy.
Other skills, from other repositories
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-improvement
WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.
review
WCAG 2.2 AA curated accessibility review — distinguishes automatically detectable, browser-assisted, and manual/human-judgment findings with evidence citations and SC mapping. Composes with design-assessment/design-improvement/frontend-design-review.
chrome-devtools
Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and Deep debugging. Pairs with playwright-cli (deterministic interaction/E2E) — complements, not duplicates.