Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mhylle/claude-skills-collection/plugin install devflowWrote 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/mhylle/claude-skills-collection/prompt-generator)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/prompt-generator"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/prompt-generator/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/mhylle/claude-skills-collection/prompt-generator"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/prompt-generator.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 | $0.00075 | $0.01318 |
| Opus 5 | $0.00037 | $0.00659 |
| Sonnet 5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
prompt-generator 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Generator
Generate structured implementation prompts for phase-based project execution using an orchestrator/subagent pattern.
Quick Start
When triggered, gather these inputs from the user:
| Variable | Description | Example |
|---|---|---|
PHASE_NUMBER |
Phase identifier | "1", "2", "3" |
PHASE_NAME |
Descriptive phase name | "Foundation", "Data Pipeline" |
PHASE_DOC_PATH |
Path to phase plan document | /project/docs/plans/01-foundation.md |
PROJECT_ROOT |
Project root directory | /home/user/myproject |
GENERAL_PLAN_PATH |
Path to general plan (optional) | /project/docs/plans/00-general-plan.md |
ADR_PATH |
Path to ADR directory (optional) | /project/docs/decisions/ |
ADR Integration: The generated prompt will instruct the orchestrator to:
- Read any ADRs referenced in the plan before implementation
- Create new ADRs when architectural decisions arise during implementation
- Update the plan with ADR references when deviating from the original design
Workflow
1. Gather User Input
Ask the user for required variables. If context provides these values, confirm them:
To generate the implementation prompt, I need:
1. Phase number (e.g., 1, 2, 3)
2. Phase name (e.g., "Foundation", "Data Pipeline")
3. Path to the phase document
4. Project root directory
5. Path to general plan (optional)
2. Generate the Prompt
Read the template from references/implementation-prompt-template.md and substitute all {PLACEHOLDER} values with user-provided inputs.
3. Output and Save
- Display: Output the complete generated prompt in the chat
- Save: Use
scripts/save_prompt.pyto save to<PROJECT_ROOT>/docs/prompts/
echo "<generated_prompt>" | python scripts/save_prompt.py <project_root> <phase_number> <phase_name>
The file is saved as: docs/prompts/phase-<N>-<name>.md
Template Features
The generated prompt includes:
- Orchestration requirements: Main session coordinates, subagents implement
- Delegation patterns: File creation, testing, infrastructure, integration
- Progress tracking: TodoWrite integration for task management
- Validation workflow: Group validation and final success criteria checks
- Error handling: Failure analysis, rollback procedures, escalation guidance
- Handoff preparation: Documentation for next phase transition
- Plan updates: Update implementation plan with actual outcomes upon completion
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 166 lines · 75 tokens per session scan A 4f920766c330
prompt-generator is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It adds 75 tokens to every session and 1,318 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…