epic-meta-prompting

epic-meta-prompting is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 0 tokens per session (1,114 once invoked), scanned A, original, MIT.

A process for generating research and planning prompts for epic work by running them in separate helper agents.

In plain words
What is it for?
Use it during the research and planning stage of an epic to investigate a technical approach and save the results.
Why use it?
It keeps research work separated from the main conversation and produces documented findings, assumptions, and open questions.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

Good fit Use it during the research and planning stage of an epic to investigate a technical approach and save the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcusgoll/spec-flow/epic-meta-prompting
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 marcusgoll/Spec-Flow --skill epic-meta-prompting
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

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 epic-meta-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/epic-meta-prompting/github.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/epic-meta-prompting)
Your own site
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/epic-meta-prompting"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/epic-meta-prompting/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 epic-meta-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/epic-meta-prompting"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/epic-meta-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 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 $0.00000 $0.01114
Opus 5.5 $0.00000 $0.00446
Sonnet 5.5 $0.00000 $0.00223
Haiku 4.5 $0.00000 $0.00111

Measured 1mo ago against content hash a4e75ab7dade, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

epic-meta-prompting 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 1mo 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/epic-meta-prompting/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic Meta-Prompting Skill

Generate research and planning prompts for epic workflows using isolated sub-agents.

Purpose

Use meta-prompting to create research and planning pipelines via /create-prompt and /run-prompt, preventing context pollution through isolated execution.

When to Invoke

  • During /epic Step 3 (Research & Planning phase)
  • After epic specification is complete and reviewed
  • Skip if resuming past the planning phase

Research Prompt Generation

/create-prompt "Research technical approach for: [epic objective]"

The create-prompt skill will:

  1. Detect purpose: Research
  2. Ask contextual questions (depth, sources, output format)
  3. Generate research prompt in .prompts/001-[epic-slug]-research/
  4. Reference relevant project docs (@docs/project/tech-stack.md)
  5. Specify XML output format with metadata

Auto-execute research prompt:

/run-prompt 001-[epic-slug]-research

Research outputs:

  • .prompts/001-[epic-slug]-research/research.md
  • Contains: findings, confidence levels, dependencies, open questions, assumptions

Copy and Commit Research

# Copy research.md to epic directory
cp .prompts/001-${EPIC_SLUG}-research/research.md epics/${EPIC_SLUG}/research.md

# Extract metadata for commit message
FINDINGS_COUNT=$(xmllint --xpath 'count(//finding)' epics/${EPIC_SLUG}/research.md)
CONFIDENCE=$(xmllint --xpath 'string(//confidence_level)' epics/${EPIC_SLUG}/research.md)
OPEN_QUESTIONS=$(xmllint --xpath 'count(//open_question)' epics/${EPIC_SLUG}/research.md)

# Commit research
git add .prompts/001-${EPIC_SLUG}-research/
git add epics/${EPIC_SLUG}/research.md
git commit -m "docs(epic-research): complete technical research for ${EPIC_SLUG}

Findings: ${FINDINGS_COUNT}
Confidence: ${CONFIDENCE}
Open questions: ${OPEN_QUESTIONS}

Next: Planning phase"

Alternative: /meta:enforce-git-commits --phase "epic-research"

Planning Prompt Generation

/create-prompt "Create implementation plan based on research"

Read the full file on GitHub · 154 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.

  1. 1mo ago First seen · 154 lines · 0 tokens per session scan A a4e75ab7dade

Subscribe to this mod's changes

epic-meta-prompting is a skill published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,114 tokens. 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 2026-09-03.