strat-creator: Skill for Claude Code

.claude/skills/strategy-refine/SKILL.md

strategy-refine is a skill for Claude Code from opendatahub-io/strat-creator. It costs 31 tokens per session (4,731 once invoked), scanned A, original, Apache-2.0.

A workflow for turning an approved feature request into a concrete implementation strategy, including how it should work and what it depends on.

In plain words
What is it for?
Use it with a strategy key to refine the implementation, record dependencies and affected components, and define operational requirements using the project's architecture.
Why use it?
It fills in details that a request describing only the desired result does not provide, while respecting local review and optional dry-run rules.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is opendatahub-io/strat-creator's own configuration. It tells Claude Code how to work on strat-creator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything strat-creator configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/strategy_history.py snapshot local/strat-tasks/<filename>.md.

Reuse

Borrowing it

Nothing to install: this file belongs to opendatahub-io/strat-creator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/opendatahub-io/strat-creator/main/.claude/skills/strategy-refine/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/strat-creator

Made for: Claude Code.

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.

agentmods badge for strategy-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/strat-creator/strategy-refine/github.svg)](https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-refine)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-refine"><img src="https://agentmods.dev/badge/skills/opendatahub-io/strat-creator/strategy-refine/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.

agentmods 80×15 button for strategy-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-refine"><img src="https://agentmods.dev/badge/skills/opendatahub-io/strat-creator/strategy-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,731 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.04731
Opus 5 $0.00015 $0.02365
Sonnet 5 $0.00006 $0.00946
Haiku 4.5 $0.00003 $0.00473

Measured 11d ago against content hash 9d9fe01693c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

strategy-refine 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 11d 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.

.claude/skills/strategy-refine/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer performing feature refinement. Your job is to take an approved RFE (the WHAT/WHY) and produce a strategy (the HOW) — grounded in the platform's actual architecture.

Dry Run Mode

If --dry-run is in $ARGUMENTS, skip ALL external writes:

  • Do NOT write or update any Jira issues
  • DO still read from Jira and local artifacts (reads are safe)
  • DO still create/update local artifacts in artifacts/strat-tasks/

Local Mode

Check if strategy files exist in local/strat-tasks/. If they do, this is a local human review session pulled via /strategy-pull.

In local mode:

  • Read strategy files from local/strat-tasks/ instead of artifacts/strat-tasks/
  • Read review files from local/strat-reviews/ instead of artifacts/strat-reviews/
  • Read originals from local/strat-originals/ instead of artifacts/strat-originals/
  • Write refined strategies to local/strat-tasks/
  • Skip ALL Jira writes (labels, description push, comments) — the push/signoff skills handle Jira at the end
  • Skip the Pipeline Label Gate — the strategy was already processed by CI; local mode is the human's turn to iterate
  • DO still fetch architecture context (needed for quality refinement)

Local mode is also active if any strategy file's frontmatter contains workflow: local.

If both local/strat-tasks/ and artifacts/strat-tasks/ have files, prefer local/strat-tasks/.

Local Architecture Context

If --architecture-context <path> is in $ARGUMENTS, link the local path before reading:

bash ${CLAUDE_SKILL_DIR}/scripts/fetch-architecture-context.sh <path>

Otherwise, if .context/architecture-context/ does not exist, fetch from remote:

bash ${CLAUDE_SKILL_DIR}/scripts/fetch-architecture-context.sh

Inputs

This skill processes exactly one strategy per invocation. $ARGUMENTS must contain a strategy key (e.g., RHAISTRAT-1531 or STRAT-001). If no key is provided, stop with an error: "No strategy key provided. Usage: /strategy-refine RHAISTRAT-NNNN"

Read the full file on GitHub · 295 lines

Files

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.

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.

  1. 11d ago First seen · 295 lines · 31 tokens per session scan A 9d9fe01693c5

Subscribe to this mod's changes

strategy-refine is a skill published in the GitHub repository opendatahub-io/strat-creator (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 4,731 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens