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 agentmods add skills/pe-menezes/vibeflow/implementnpx skills add pe-menezes/vibeflow --skill implementgit clone --depth 1 https://github.com/pe-menezes/vibeflowWhat 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 | $0.00079 | $0.02141 |
| Opus 5 | $0.00039 | $0.01071 |
| Sonnet 5 | $0.00016 | $0.00428 |
| Haiku 4.5 | $0.00008 | $0.00214 |
Grade A, and why
implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- vibeflow-implement — 91% identical, 48 lines differ
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Description and examples
What it does: Reads a spec from .vibeflow/specs/ (or by path), loads applicable patterns and conventions from .vibeflow/, identifies target files, and implements the feature following all spec guardrails (DoD, budget, anti-scope, pattern compliance). Runs tests and self-verifies each DoD check before finishing. This command puts the agent in Coding Agent mode — it follows the spec, it does NOT make architectural decisions.
Examples:
/vibeflow:implement .vibeflow/specs/auto-install.md— Implement from spec file path./vibeflow:implement auto-install— Same; agent finds the spec by feature name in.vibeflow/specs/./vibeflow:implement .vibeflow/specs/auth-part-2.md— Implement part 2 of a multi-part spec (checks that part 1 dependencies are satisfied first).
Language
Detect the language of the user's input ($ARGUMENTS or conversation). Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
Implement from spec: $ARGUMENTS
Role: Coding Agent
You are a coding agent: the spec decides, you execute. Deliver what the spec asks, at the scope it defines. Make routine judgment calls yourself; check in only when different readings would lead to materially different work. If the spec seems mistaken, say so in a sentence and continue as specified. Finish the whole task, and stop short of changes clearly beyond it.
Architectural decisions belong to the architect. When the spec doesn't cover a design choice, or is ambiguous on a point that matters, stop and ask instead of deciding.
Phase 0: Find and validate the spec
- Locate it. A file path (contains
/or ends in.md) is read directly. A feature name is matched in.vibeflow/specs/— exact ($ARGUMENTS.md), then partial; several matches → list them and ask the user to choose; none → list the available specs and suggest/vibeflow:gen-spec. - Validate required sections: Definition of Done (at least 1 check), Scope
("Escopo"), Anti-scope ("Anti-escopo"). If any is missing, stop, list
what's absent, and point to
/vibeflow:gen-spec. - Dependencies: each spec listed under Dependencies needs an audit report
in
.vibeflow/audits/with verdict PASS. If one lacks it, stop and list what must be implemented and audited first, in order. If no audits directory exists at all, warn ("Dependencies listed but no audit reports found — verify they are already implemented") and proceed.
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.
- 3d ago First seen · 224 lines · 79 tokens per session scan A 79ca15794d99
implement is a skill published in the GitHub repository pe-menezes/vibeflow (29 stars, last pushed 14d ago), licensed MIT. It adds 79 tokens to every session and 2,141 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing.".
apm-review-panel
Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
apm-triage-panel
Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.
pr-description-skill
Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a…
docs-sync
Use this skill whenever a pull request is opened, reopened, or synchronized in microsoft/apm to assess whether and how the documentation corpus must change to stay truthful with the proposed code change. Activate even when the PR title or body says nothing about docs -- the skill must run on every PR to detect silent…