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/josix/agent-flow/prompt-refinementnpx skills add josix/agent-flow --skill prompt-refinementgit clone --depth 1 https://github.com/josix/agent-flowWrote 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/josix/agent-flow/prompt-refinement)<a href="https://agentmods.dev/skills/josix/agent-flow/prompt-refinement"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/prompt-refinement.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01806 |
| Opus 5 | $0.00018 | $0.00903 |
| Sonnet 5 | $0.00007 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
prompt-refinement 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 4d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Refinement
Overview
Prompt refinement transforms ambiguous or incomplete user requests into clear, structured task specifications suitable for multi-agent orchestration. This skill bridges natural language input and the precise specifications required by downstream agents.
Purpose
Ensure tasks entering the orchestration pipeline have:
- Clear Objectives: A single, well-defined goal that can be verified
- Actionable Steps: Concrete actions that agents can execute
- Measurable Outcomes: Success criteria that verification agents can check
- Appropriate Scope: Boundaries that prevent scope creep
When to Use This Skill
Apply prompt refinement when:
- User input contains ambiguous terms ("fix it", "make it better")
- The request lacks specific targets (files, components, systems)
- Multiple interpretations of the request are possible
- Pre-processing is required for
/orchestrateor/plancommands
Key Principles
- Ask First, Act Second: When genuinely ambiguous, clarify before proceeding
- One Question at a Time: Never overwhelm users with multiple clarification requests
- Provide Options: Give concrete choices to speed up clarification
- Default Gracefully: Make reasonable assumptions when users don't respond
- Preserve Intent: Refinement should clarify, not change the user's goal
Refinement Template
Standard Format
**Goal**: <one-sentence objective stating what will be accomplished>
**Description**: <2-3 sentences providing context and scope>
**Actions**:
1. <specific, atomic action with clear target>
2. <specific, atomic action with clear target>
3. ...
**Constraints**: <what must not be broken, changed, or violated>
**Assumptions**: <what is taken for granted — surfaces risks early>
Template Guidelines
| Field | Requirements | Example |
|---|---|---|
| Goal | Single sentence, verb-first, specific outcome | "Implement rate limiting on /api/users endpoint" |
| Description | Context, scope boundaries | "Add rate limiting to prevent API abuse. Limit to 100 req/min per IP." |
| Actions | Numbered, ordered, atomic steps | "1. Explore existing middleware patterns" |
| Constraints | Non-negotiable requirements; what must stay intact | "Must not alter existing auth cookie format" |
| Assumptions | Preconditions taken for granted | "Redis is already provisioned" |
What ships with it
5 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.
- 4d ago First seen · 254 lines · 36 tokens per session scan A eb9c1e4426e7
prompt-refinement is a skill published in the GitHub repository josix/agent-flow (7 stars, last pushed 19d ago), licensed MIT. It adds 36 tokens to every session and 1,806 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
ship-and-babysit
End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成（shogun-imagegenを使え）。.
shogun-agent-status
全エージェント（家老・足軽1-7・軍師）の稼働状態を一覧表示するスキル。tmux pane状態（稼働中/待機中/不在）とタスクYAML状態（taskid, status）と未読inbox数を統合表示。「稼働確認」「エージェント状態」「布陣確認」「agent status」で起動。.