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 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/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/josix/agent-flow/prompt-refinement"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/prompt-refinement.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 | $0.00036 | $0.01813 |
| Opus 5.5 | $0.00014 | $0.00725 |
| Sonnet 5.5 | $0.00007 | $0.00363 |
| 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 27d 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 — 255 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.
- 27d ago Changed · +1 lines 5c4052050867
- 1mo 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 (8 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,813 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.