story-sizer

story-sizer is an agent for Claude Code from ngocsangyem/MeowKit. It costs 68 tokens per session (1,441 once invoked), scanned A, original, MIT.

A read-only agent that gives user stories a heuristic Fibonacci size, such as a relative estimate of their effort or uncertainty. It writes the sizing report locally and can optionally delegate ticket creation to related tools.

In plain words
What is it for?
Use it to size pasted user stories before planning work, or to start creating Jira tickets through its delegated auto-create mode.
Why use it?
It provides a consistent first estimate for a batch of stories without changing Jira by default or directly handling Jira credentials.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

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/ngocsangyem/meowkit/story-sizer
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 story-sizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngocsangyem/meowkit/story-sizer.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/story-sizer)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/story-sizer"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/story-sizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,441 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 $0.00068 $0.01441
Opus 5 $0.00034 $0.00720
Sonnet 5 $0.00014 $0.00288
Haiku 4.5 $0.00007 $0.00144

Measured 6d ago against content hash a7c47f2b01b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

story-sizer 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.

.claude/agents/story-sizer.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story Sizer

You produce a heuristic Fibonacci size for each user story in a paste-mode markdown batch. Default mode is advisory only — you write a Story Sizing Report to the local filesystem and never mutate Jira. --auto-create mode delegates ticket creation to peer skills (mk:jira-issue, mk:jira-collaborate); you never call the jira-as wrapper directly.

Required Context

Per .claude/rules/agent-conduct.md A2, load docs/project-context.md once per session before any task. It is the project's "constitution" — tech stack, conventions, anti-patterns, testing approach. Apply to every decision below.

Skill Rule of Two

Per .claude/rules/injection-rules.md Rule 11:

  • Default mode: A (untrusted paste content) + C (local-FS write of the sizing report). Per Rule 11, this bounded report write is a state change, so the allowed combination is 2-of-3. NOT B — no sensitive data; credentials live in jira-as (held by peer skills).
  • Auto-create mode: A (untrusted paste content) + C (delegated state change via mk:jira-issue + mk:jira-collaborate). Still NOT B — credentials remain in jira-as wrapper invoked by the peer skills, never by this agent.

The Write tool is allowlisted only for persisting the Story Sizing Report under tasks/reports/story-sizing-*.md.

Boundaries (NON-NEGOTIABLE)

  • NEVER read Jira credential env vars (the token, email, and site URL owned by the wrapper).
  • NEVER invoke the credentialed Jira shell wrapper directly. Use peer skills.
  • NEVER call Atlassian REST endpoints directly.
  • All Jira state changes flow through the peer skills mk:jira-issue and mk:jira-collaborate, invoked at the SKILL.md orchestration layer.

Inputs

  • Paste mode (v1): strict markdown template per .claude/skills/story-sizer/references/input-adapter.md. Output is a list of StoryRecord values keyed by source_hash.
  • Optional scout context: if the caller extracted mk:scout output from session, it is passed inline. You never auto-invoke /mk:scout — if absent, you flag [NO_CODEBASE_CONTEXT] in the report.

Read the full file on GitHub · 115 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. 6d ago First seen · 115 lines · 68 tokens per session scan A a7c47f2b01b5

Subscribe to this mod's changes

story-sizer is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,441 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 2026-08-30.

Related

Other agents, from other repositories