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-claude --skill analyzegit clone --depth 1 https://github.com/pe-menezes/vibeflow-claudeWrote 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-claude/analyze)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow-claude/analyze"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow-claude/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-claude/analyze"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow-claude/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 | $0.00081 | $0.07125 |
| Opus 5.5 | $0.00032 | $0.02850 |
| Sonnet 5.5 | $0.00016 | $0.01425 |
| Haiku 4.5 | $0.00008 | $0.00713 |
Grade C, and why
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
95% identical to analyze — 0 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 — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description and examples
What it does: Scans the codebase and generates (or updates) .vibeflow/: index, conventions, and one pattern doc per significant pattern. Use once for project setup, then after big changes or to deep-dive into a module.
Examples:
analyze— First run or incremental (only re-analyzes what changed since last run).analyze --fresh— Rebuild everything from scratch; ignore existing.vibeflow/.analyze --scope src/app— Deep-dive intosrc/apponly; requires.vibeflow/to already exist. Enriches pattern docs with examples from that module.analyze --interactive— Run analysis with interactive review: validate patterns, remove false positives, add tribal knowledge before saving.analyze --fresh --interactive— Full rebuild with interactive review.analyze --satellite https://github.com/org/design-system— Analyze a dependency repo, keep only patterns your code uses, merge into.vibeflow/patterns/satellite-<name>/.analyze --measure— Also 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.
Web Search Policy
Use WebSearch and WebFetch only when local context (.vibeflow/, codebase,
git history) is insufficient — an unfamiliar framework or API. Local first.
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
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 · +47 lines 6a15d75f8130
- 1mo ago Changed · +5 lines 2c41432a0534
- 1mo ago First seen · 591 lines · 81 tokens per session scan C e0df157e585e
analyze is a skill published in the GitHub repository pe-menezes/vibeflow-claude (2 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 7,125 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 95% identical to analyze, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…