fill-cycle

fill-cycle is a skill for Claude Code, Codex from stoa-platform/stoa. It costs 23 tokens per session (2,373 once invoked), scanned A, original, Apache-2.0.

A sprint-planning tool that measures how much work a Linear cycle can still hold and suggests backlog items to reach 80% of the team’s demonstrated delivery pace. A backlog is the list of work waiting to be done, and a cycle is a planned work period.

In plain words
What is it for?
Use it to calculate a capacity report, scan four backlog sources, filter candidates by roadmap theme, create a fill plan, or automatically promote smaller tasks when using its automatic mode.
Why use it?
Teams may start a sprint with too little work or choose additional tasks without checking their actual capacity. This compares the current cycle with past delivery pace and ranks suitable work to fill the gap.

Skill for Claude CodeCodex

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/stoa-platform/stoa/fill-cycle
Any agent
npx skills add stoa-platform/stoa --skill fill-cycle
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code, Codex.

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 fill-cycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/stoa-platform/stoa/fill-cycle.svg)](https://agentmods.dev/skills/stoa-platform/stoa/fill-cycle)
Your own site
<a href="https://agentmods.dev/skills/stoa-platform/stoa/fill-cycle"><img src="https://agentmods.dev/badge/skills/stoa-platform/stoa/fill-cycle.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,373 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 $0.00023 $0.02373
Opus 5 $0.00012 $0.01187
Sonnet 5 $0.00005 $0.00475
Haiku 4.5 $0.00002 $0.00237

Measured 4d ago against content hash c7e9bea9cda7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fill-cycle 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.

.claude/skills/fill-cycle/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fill Cycle — Velocity Pipeline

Load the current Linear cycle, compute the capacity gap against proven velocity, scan 4 backlog sources, and propose a ranked fill plan.

Target: $ARGUMENTS

Linear Label IDs (cached)

Label ID
roadmap (parent group — NOT assignable to issues) <LABEL_ID_ROADMAP>
roadmap:gateway <LABEL_ID_ROADMAP_GATEWAY>
roadmap:dx <LABEL_ID_ROADMAP_DX>
roadmap:platform <LABEL_ID_ROADMAP_PLATFORM>
roadmap:community <LABEL_ID_ROADMAP_COMMUNITY>
roadmap:observability <LABEL_ID_ROADMAP_OBSERVABILITY>

Step 0: Determine Mode

Argument Mode Description
(empty) Interactive Show fill plan, ask before promoting
--check Read-only Compute capacity report only, no writes (CI-safe)
--auto Auto-promote Promote quick wins automatically, suggest council for MEGAs
--theme <name> Themed fill Filter candidates by roadmap theme + optional Notion search

Step 1: Fetch Current Cycle from Linear

linear.list_cycles(teamId: "<LINEAR_TEAM_ID>")

Identify the current cycle (type "current" or date range containing today). Extract: cycle_id, name, start, end, scopeTotal, completedTotal.

Then fetch all issues in the cycle:

linear.list_issues(
  team: "<LINEAR_TEAM_ID>",
  cycle: "<cycle_id>",
  first: 50
)

Compute:

  • cycle_days = (end - start).days
  • days_remaining = (end - today).days
  • pts_committed = sum of all issue estimates in cycle
  • pts_done = sum of estimates for Done/Canceled issues

Step 2: Read Velocity Baseline

Read .claude/state/velocity.json.

Extract:

  • rolling_avg_pts_per_day = rolling_avg_3.pts_per_day
  • target_utilization (default 0.80)

Compute capacity gap:

capacity = rolling_avg_pts_per_day × cycle_days
target = capacity × target_utilization
gap = target - pts_committed

If gap <= 0: report "Cycle is fully loaded" and stop (unless --check which still reports).

Read the full file on GitHub · 277 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 · 277 lines · 23 tokens per session scan A c7e9bea9cda7

Subscribe to this mod's changes

fill-cycle is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,373 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 2026-08-31.