wise-estimation

wise-estimation is a skill for Claude Code, Codex from e1024kb/wise-claude. It costs 128 tokens per session (1,288 once invoked), scanned A, original, MIT.

A reference for estimating development work with story points, using a Fibonacci-like scale from 0.5 to 13. Story points compare complexity, scope, uncertainty, and effort rather than measuring exact hours.

In plain words
What is it for?
Use it when assigning story points to frontend, backend, mobile, or platform work, deciding between sizes, or identifying tickets that should first become research tasks.
Why use it?
It gives teams a shared way to size tickets, including work that is too uncertain or large to estimate confidently as a normal implementation task.

Skill for Claude CodeCodex

Part of the wise plugin — 32 skills, 22 agents, 1 hook shipped together

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 skills/e1024kb/wise-claude/wise-estimation
Any agent
npx skills add e1024kb/wise-claude --skill wise-estimation
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Made for: Claude Code, Codex.

Or install wise, the plugin that ships this one along with the rest of its 32 skills, 22 agents, 1 hook.

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 wise-estimation

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-estimation.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-estimation)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-estimation"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-estimation.svg" alt="Measured on agentmods" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 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 $0.00128 $0.01288
Opus 5 $0.00064 $0.00644
Sonnet 5 $0.00026 $0.00258
Haiku 4.5 $0.00013 $0.00129

Measured 4d ago against content hash e40d6b3084b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wise-estimation 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 4d 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.

plugins/wise/skills/wise-estimation/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Story-Point Estimation

Canonical story-point (SP) scale for sizing Jira tickets. Applies to every team (frontend, backend, mobile, platform) — using the same units so cross-team planning works.

This is a reference doc, not a procedure. When the user is planning a ticket or breaking work into tasks, consult this scale to pick a value; when the user asks "is this a 3 or a 5?", walk the complexity/scope/time axes below to decide.

The scale

Fibonacci, with a 0.5 minimum for truly trivial work.

SP Complexity Typical scope Calendar time
0.5 Trivial, mechanical Single file, one obvious change (copy tweak, constant rename, one-line config) ~half day
1 Simple, well-understood 1–2 files, clear requirements, pattern already exists ~1 day
2 Moderate 3–5 files, some decisions to make, one or two unknowns ~2 days
3 Complex Multiple components, non-trivial logic, meaningful test surface ~3 days
5 Large feature Architecture decisions, several components, full test coverage ~1 week
8 Epic-level Multiple sub-tasks, crosses file/module boundaries, touches API + UI ~2 weeks
13 Major feature with unknowns Research needed, spec not fully baked, architecture open ~3 weeks+

How to pick a number

Size against three axes. The estimate is the HIGHEST of the three, not the average — an unfamiliar-tech ticket with one file is still not a 1.

  1. Scope — how many files, components, or systems change?
  2. Complexity — how much decision-making, algorithmic work, or cross-cutting coordination is involved?
  3. Uncertainty — how much of the work is genuinely understood up-front vs. will-need-to-figure-it-out-as-we-go?

Examples:

  • Change a button colour across one component + its story → 0.5 (low on all three).
  • Add a new field to an existing form, with validation, backend wiring, and tests → 2 (scope drives it).
  • Rewrite a contested caching layer with existing patterns → 3 (complexity drives it).
  • Integrate a third-party SDK we've never used → 5 minimum (uncertainty drives it, even if the file count is small).

Read the full file on GitHub · 114 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. 4d ago First seen · 114 lines · 128 tokens per session scan A e40d6b3084b7

Subscribe to this mod's changes

wise-estimation is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 9d ago), licensed MIT. It adds 128 tokens to every session and 1,288 once invoked, about $0.0006 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 2026-08-31.