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 aenix-io/aeman --skill derive-capacitygit clone --depth 1 https://github.com/aenix-io/aemanWrote 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/aenix-io/aeman/derive-capacity)<a href="https://agentmods.dev/skills/aenix-io/aeman/derive-capacity"><img src="https://agentmods.dev/badge/skills/aenix-io/aeman/derive-capacity/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/aenix-io/aeman/derive-capacity"><img src="https://agentmods.dev/badge/skills/aenix-io/aeman/derive-capacity.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 | $0.00072 | $0.01702 |
| Opus 5 | $0.00036 | $0.00851 |
| Sonnet 5 | $0.00014 | $0.00340 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
derive-capacity 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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Derive a capacity
A person's CAPACITY on the aeman board is the points a week they get through. The board measures their load against it — "21/40" over the column, red past it — and it is the only number a lead has for saying "this week does not fit".
The board never derives it. It could, and this skill is that arithmetic — but a number a board prints beside a name reads as a fact, and this one is only as good as the record it comes from. So it is derived HERE, by somebody who can see how thin the record is, shown to the lead, and written back as their judgement.
Before anything: is the record long enough?
doneAt is only written from the day a board started keeping it. A window that is empty of RECORDS while being full of WORK produces a median far under the truth, and nothing on screen says so.
list_cards view=all stage=doneand readstatus.doneAton every card. Find the earliest one. (Done is DERIVED from progress, never stored on a card — the selector asks the board's own question, so this is the one placestage=donemeans anything.)- Compare it against the four complete weeks before this one (Monday to Monday; this week never counts — it is not over).
- If the earliest
doneAtis inside that window, the record does not cover it. Say so first, in the answer, before any number: how many complete weeks are actually covered, and that everything below is a floor, not a capacity. Two covered weeks is worth showing as "at least N"; less than two is not worth deriving at all — tell the lead to set the numbers from what they know and come back in a month.
Also check how much is SIZED: spec.size on the closed cards. An unsized card weighs M, so a board where few cards are sized gives you a count of cards in M-equivalents, not a weight of work. If most closed cards are unsized, run size-cards over the window first, or say plainly that the number is a card count in disguise.
The arithmetic
Over the last four complete weeks, per person:
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.
- yesterday First seen · 67 lines · 72 tokens per session scan A 0b0e92844aa3
derive-capacity is a skill published in the GitHub repository aenix-io/aeman (31 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 1,702 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
scrumboy-board-operator
Operate Scrumboy projects and boards through MCP or Agoragentic APIs. Use when an agent needs to inspect board state, plan sprint work, create todos, move cards, manage tags, or summarize project health.
project-management
Agile methodologies, issue tracking, and team collaboration tools.
machinist
Use Machinist to create, assign, monitor, and resume software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, lifecycle labels, direct runs, or managed queue.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
gr-product-dev-ops
🇺🇸 Your dev team ships features nobody asked for while user-reported bugs pile up for months. Operations blames engineering for ignoring users; engineering blames operations for not understanding technical constraints. This gives you the complete Product × Engineering × Operations alignment SOP — from unified…
miro-workflow
Compose Miro boards from natural-language requests by combining tools from miro-mcp-server. Use when the user asks to set up a sprint board, retrospective, brainstorming session, user story map, kanban, or any structured Miro layout. Do NOT use for single-tool calls (create one sticky), questions about Miro the…