user-story-capture

user-story-capture is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 94 tokens per session (1,350 once invoked), scanned A, original, MIT.

A tool that turns exploration notes, prototypes, and business documents into prioritised user stories with acceptance criteria. It can use either the “As a / I want / So that” format or Gherkin’s “Given / When / Then” format.

In plain words
What is it for?
Use it to prepare the first implementation slice, group related user needs, set priorities, and write acceptance criteria for development and testing.
Why use it?
It reduces the work of turning scattered discovery material into clear, testable requirements. It also highlights missing information before implementation starts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the exploration-cycle-plugin plugin — 20 skills, 15 agents shipped together

Good fit Use it to prepare the first implementation slice, group related user needs, set priorities, and write acceptance criteria for development and testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richfrem/agent-plugins-skills/user-story-capture
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 richfrem/agent-plugins-skills --skill user-story-capture
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install exploration-cycle-plugin, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

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 user-story-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/user-story-capture/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/user-story-capture)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/user-story-capture"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/user-story-capture/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 user-story-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/user-story-capture"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/user-story-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00094 $0.01350
Opus 5 $0.00047 $0.00675
Sonnet 5 $0.00019 $0.00270
Haiku 4.5 $0.00009 $0.00135

Measured 7d ago against content hash 99d544090114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

user-story-capture 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/execute.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/exploration-cycle-plugin/skills/user-story-capture/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Story Capture

Derive structured user stories and acceptance criteria from exploration session captures.

Usage

python ./scripts/execute.py \
  --input <file> [<file2>...] \
  --format <standard|gherkin> \
  --output <output_file.md>

Formats:

  • standard (default): As a [user type], I want [goal], so that [benefit] — with priority table and gaps.
  • gherkin: Standard + Given / When / Then Acceptance Criteria blocks per story.

Flags:

  • --input PATH [PATH ...] : Session brief, BRD draft, prototype notes, or prior captures
  • --output PATH : Destination file (default: exploration/captures/user-stories-draft.md)
  • --format FORMAT : Output format (default: standard)

Interactive Co-Authoring Workflow

When invoked interactively, follow this 3-stage pattern. Do not dump a full story list at once.

Stage 1: Context Gathering

Ask all three questions in a single message before generating anything:

  1. Input files: Which source documents should I work from? (Check exploration/ — list what you find: session brief, BRD draft, prototype notes.) If no files exist, stop and ask for input before proceeding.
  2. Primary actor: Which user role, system actor, or job-to-be-done is the highest priority for the first implementation slice? (Use role-neutral language — e.g., "the person approving requests", "the agent running evals", not just "the user".)
  3. Out-of-scope: Are there any actors or workflows we should explicitly exclude from this story set?
  4. Format: Should acceptance criteria use standard format (As a / I want / So that) or Gherkin (Given / When / Then)? Default to standard unless Gherkin is requested.

After the user responds: read each input file they identify.

Stage 2: Iterative Refinement

Build the backlog in layers — do not jump straight to full Gherkin blocks.

  1. Outline first: Based on the input files and primary actor, present a numbered list of lightweight story titles (one line each, no ACs yet). Ask: "Which of these should we keep, cut, or merge for the first slice?"
  2. Curate: Apply changes. Mark any story derived from unclear or inferred source material as [UNCONFIRMED].
  3. Draft approved stories: For each kept story, write the full format:
    • Standard: As a [actor], I want [goal], so that [benefit].
    • Gherkin: Add Given / When / Then AC blocks after the story statement.

Read the full file on GitHub · 100 lines

Files

What ships with it

6 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. 7d ago First seen · 100 lines · 94 tokens per session scan A 99d544090114

Subscribe to this mod's changes

user-story-capture is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,350 once invoked, about $0.0005 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 2026-09-03.