A self-contained instruction document generated from a feature specification, including the task, completion checks, limits, and relevant code patterns. It is meant to be handed to another coding agent that may not have the repository context.

Use it to prepare an implementation handoff from a spec. It saves the resulting prompt pack under .vibeflow/prompt-packs/.

It reduces the information another agent needs to reconstruct before implementing the work. The input does not describe the generated document's full format beyond its saved location.

prompt-pack — Skill for Claude Code by pe-menezes

Install

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.

Any agent

npx skills add pe-menezes/vibeflow --skill prompt-pack

Clone the repo

git clone --depth 1 https://github.com/pe-menezes/vibeflow

Made for: Claude Code.

Or install vibeflow, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pe-menezes/vibeflow/prompt-pack/github.svg)](https://agentmods.dev/skills/pe-menezes/vibeflow/prompt-pack)

Your own site

<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/prompt-pack"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/prompt-pack/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pe-menezes/vibeflow/prompt-pack"><img src="https://agentmods.dev/badge/skills/pe-menezes/vibeflow/prompt-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,173 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Prompt Injection · line 41
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00063	$0.01173
Opus 5	$0.00032	$0.00587
Sonnet 5	$0.00013	$0.00235
Haiku 4.5	$0.00006	$0.00117

Measured 3d ago against content hash ffcb77eefe40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-pack 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

prompt-pack — 91% identical, 0 lines differ

plugins/vibeflow/skills/prompt-pack/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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 path), builds a single prompt that includes objective, DoD, anti-scope, and real code patterns. Saves to .vibeflow/prompt-packs/<slug>.md. Give that file to the coding agent so it implements without needing the rest of the repo context.

Examples:

prompt-pack .vibeflow/specs/login-flow.md — Generate prompt pack from the login-flow spec.
prompt-pack login-flow — Same; agent finds the spec by name.

Language

Write the whole pack — opening line, objective, DoD, anti-scope, guidance — in the user's detected language. Code, paths, and technical names stay in English.

Generate a self-contained prompt pack for the spec in the user's current request.

Steps

Validate spec size. Read the spec: more than 7 DoD checks, or over the budget (the spec's Budget field, else the Suggested budget line in .vibeflow/index.md, else ≤6 files), and you stop without generating the pack — tell the user it exceeds limits (N checks / N files) and to run gen-spec again to split it first.
Locate the spec: a file path is read directly; a feature description is matched against .vibeflow/specs/. No spec exists → generate one in the gen-spec format, save it, then continue.
Read .vibeflow/conventions.md, plus the pattern docs the spec lists under Applicable Patterns. If it lists none, resolve them: read the ## Pattern Registry block in index.md (between  markers) and cross-reference its tags and modules against the spec's scope — top 3–5 matches; with no registry, infer which are relevant.
Read the codebase files this task touches, plus anything the spec lists under References.
Generate the pack.

The pack opens with

You are only seeing this prompt; there is no context outside it.

Then, in this order

1. Objective and Definition of Done

From the spec. Non-negotiable.

Read the full file on GitHub · 129 lines

Changes

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 Changed · -1 lines · +3 tokens per session ffcb77eefe40
10d ago First seen · 130 lines · 60 tokens per session scan A ac83f47068d2

Subscribe to this mod's changes

prompt-pack is a skill published in the GitHub repository pe-menezes/vibeflow (29 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,173 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 2026-08-30.

Building agents Claude Code Planning ai-agents cursor developer-tools github-copilot prompt-engineering

prompt-pack

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

Description and examples

Language

Steps

The pack opens with

Then, in this order

1. Objective and Definition of Done

What this file has done since we first saw it

Other skills, from other repositories

copilot-setup-audit

copilot-compatibility-checker

copilot-skill-builder

personetta-set-active

personetta-current

personetta-list