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 tmj-90/gaffer --skill user-storygit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/user-story)<a href="https://agentmods.dev/skills/tmj-90/gaffer/user-story"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/user-story/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/tmj-90/gaffer/user-story"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/user-story.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 | $0.00053 | $0.00810 |
| Opus 5 | $0.00026 | $0.00405 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
user-story 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate structured user stories with acceptance criteria
A user story is not a task list — it's a unit of user value that can be independently delivered and tested.
Story format
As a [specific user role],
I want to [action / capability]
so that [outcome / value].
Acceptance criteria:
- Given [context], when [action], then [observable outcome].
- Given [context], when [error condition], then [error handling].
Anti-patterns to reject:
- "As a user" (too vague — which user?)
- Stories without AC ("it should work")
- Stories that describe implementation ("add a button") instead of value ("so that I can...")
- Stories > 8 story points (split them)
Story sizing heuristic (Fibonacci)
| Points | Scope |
|---|---|
| 1 | Trivial — confident implementation; no unknowns |
| 2 | Small — clear implementation; minor unknowns |
| 3 | Medium — clear approach; some complexity |
| 5 | Large — approach known; meaningful unknowns or cross-cutting |
| 8 | Extra large — approach uncertain; split if possible |
| 13+ | Epic — must be split before sprint planning |
INVEST principles (every story should satisfy all six)
- Independent — can be delivered without depending on another in-progress story.
- Negotiable — the how is open; the what and why are fixed.
- Valuable — delivers value to a real user, not just to engineering.
- Estimable — the team can size it; unknowns are identified.
- Small — fits in a sprint; ≤ 8 points.
- Testable — ACs allow a tester to confirm done from not-done.
Sprint planning
Given a capacity (in story points) and a prioritised backlog:
- Sort stories by priority (impact × confidence / effort).
- Take from the top until capacity is consumed.
- Flag any story ≥ 8 points — must be split before it enters the sprint.
- Confirm each story in the sprint satisfies INVEST.
Steps
- Gather context. Feature or epic description; user personas available; any existing requirements or PRD.
- Identify the user roles involved. For each distinct role, generate stories independently.
- Write stories in standard format. One value unit per story; INVEST check for each.
- Write at least two ACs per story. Happy path + at least one error/edge case.
- Size each story. Flag 8+ for splitting.
- For sprint planning — sort by priority; fill to capacity; confirm no 13+ point stories in the sprint.
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.
- 6d ago First seen · 80 lines · 53 tokens per session scan A e9f9ceb8787f
user-story is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 810 once invoked, about $0.0003 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.
Other skills, from other repositories
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.