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-statsgit 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-stats)<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/vibeflow-stats"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/vibeflow-stats/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-stats"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/vibeflow-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01245 |
| Opus 5.5 | $0.00018 | $0.00498 |
| Sonnet 5.5 | $0.00009 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
vibeflow-stats 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 today.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibeflow: Stats
Show statistics from audit reports. Reads all audits and compiles
pass/fail rates, most violated patterns, and common DoD gaps; with loop
ledgers in .vibeflow/loop/, also the loop's rounds, fix rounds,
first-audit PASS and clock from dispatch to PASS.
Usage: Run this skill with no input. It reads .vibeflow/audits/.
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.
Steps
-
Read every
.mdfile in.vibeflow/audits/. If there are none and.vibeflow/loop/holds no ledger (a.mdfile there other thanconfig.md, step 3), report "No audits found. Run the vibeflow-audit skill after implementing a feature." and stop. -
From each audit take the verdict (the
**Verdict:**line), the[x]/[ ]counts under### DoD Checklist, the patterns marked[ ]under### Pattern Compliance, and the items under### Convention Violations. A file in a different shape contributes what it can, noted as "Non-standard format detected in ." A report with**Verdict: pending**is an audit in progress or interrupted: count it apart, as "N audits in progress or interrupted", and leave it out of every other count in this report: Audits analyzed, the PASS, PARTIAL and FAIL counts and their percentages, the DoD, pattern and convention counts, the Trend, and the finding,closed-by-probeandIndependence:counts of step 3. -
The ledgers are the
.mdfiles in.vibeflow/loop/other thanconfig.md, which holds the loop's settings and is not a ledger. When there is at least one ledger, build the Loop section; with none, leave the section out, since the loop is opt-in.- Run
node .cursor/skills/vibeflow-implement/loop/scripts/loop-stats.mjs <project root> --json. Its parts, totals and warnings are the loop numbers: report them as they come rather than recounting the rounds tables, because the script skips a malformed row instead of guessing it. Exit 64 means it could not run; quote its message and leave the numbers out. - When
.cursor/skills/vibeflow-implement/loop/is missing, the loop kit is not installed: say thatnpx setup-vibeflow@latest --cursor --force(setup-vibeflow 0.17.0 or newer) installs it, and report the rest. - From the audit reports, count the finding lines
(
- [<id>] <severity> · <cause> · confidence ...) by severity (defect,risk-gap,low) and by cause (spec,implementation,proof,fix), the findings markedclosed-by-probe, and the reports by theirIndependence:line (fresh sessionagainstsame session). Reports written before these fields existed stay out of these counts.
- Run
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.
- today Changed · +44 lines 99fced64a9f3
- 1mo ago First seen · 69 lines · 46 tokens per session scan A f414bdfabb1f
vibeflow-stats is a skill published in the GitHub repository pe-menezes/vibeflow (32 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,245 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
confluence-permission
Manage space and page permissions and restrictions. ALWAYS use when user wants to control access, set restrictions, or manage who can view/edit content.
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.