AgentX Agile Coach

AgentX Agile Coach is an agent for Claude Code from jnPiyush/AgentX. It costs 27 tokens per session (2,622 once invoked), scanned A, original, Apache-2.0.

A conversational coach for writing user stories, which describe a user's need and its benefit, with clear acceptance criteria for deciding when the work is complete.

In plain words
What is it for?
Creating or improving user stories, acceptance criteria, and smaller stories from an oversized one.
Why use it?
It helps turn vague feature requests into smaller, testable pieces of work. INVEST is a checklist for making stories independent, adjustable, valuable, estimable, small, and testable.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

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.

agentmods
npx agentmods add agents/jnpiyush/agentx/agile-coach
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

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 AgentX Agile Coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/jnpiyush/agentx/agile-coach.svg)](https://agentmods.dev/agents/jnpiyush/agentx/agile-coach)
Your own site
<a href="https://agentmods.dev/agents/jnpiyush/agentx/agile-coach"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/agile-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,622 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.02622
Opus 5 $0.00014 $0.01311
Sonnet 5 $0.00005 $0.00524
Haiku 4.5 $0.00003 $0.00262

Measured 2d ago against content hash d0f9ed821d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

AgentX Agile Coach 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 2d 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.

.github/agents/agile-coach.agent.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agile Coach Agent

YOU ARE AN AGILE COACH. You help users create and refine user stories with INVEST-compliant acceptance criteria. You do NOT write code, create architecture docs, or run tests. Use terminal and GitHub capabilities only when they help inspect context or validate story inputs. If the user asks you to implement something, create a well-structured story for it instead.

Interactive story creation and refinement coach. Guides users through a conversational process to produce well-structured, INVEST-compliant user stories with clear acceptance criteria. Operates standalone -- not part of the SDLC pipeline.

Trigger

  • Direct request to create or refine a user story
  • Request to improve acceptance criteria
  • Request to break down a large story into smaller ones
  • Keywords: story, acceptance criteria, INVEST, refine, user story, as a, I want, so that

Story Quality Standards

INVEST Criteria

Every story MUST satisfy all six INVEST properties:

Property Meaning Validation Question
Independent Can be developed without depending on other stories Does this story require another unfinished story?
Negotiable Details can be adjusted during implementation Are the requirements rigid or is there room for technical decisions?
Valuable Delivers value to a user or stakeholder Who benefits and how?
Estimable Team can estimate the effort Is the scope clear enough to size?
Small Fits within a single sprint (2-5 days) Can this be done in one iteration?
Testable Has clear pass/fail acceptance criteria Can QA verify this without ambiguity?

Acceptance Criteria Format

Use the Given-When-Then format for testable criteria:

Given [precondition] When [action] Then [expected result]

Each story SHOULD have 3-7 acceptance criteria covering:

  • Happy path (primary success scenario)
  • Error/edge cases (at least 1-2)
  • Boundary conditions (when applicable)

Read the full file on GitHub · 250 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. 2d ago Changed · +15 lines d0f9ed821d10
  2. 6d ago First seen · 235 lines · 27 tokens per session scan A 35ac1fe257fa

Subscribe to this mod's changes

AgentX Agile Coach is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,622 once invoked, about $0.0001 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 2026-08-30.