sprint-planning

A collaborative process for planning a development sprint, which is a short period of focused work toward selected tasks.

In plain words
What is it for?
Use it to validate candidate issues, set priorities, define acceptance criteria, assess dependencies and risks, and create a task queue.
Why use it?
It checks whether reported issues still exist and combines product, architecture, process, and development perspectives before work is assigned.

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/loopdive/js2/sprint-planning
Any agent
npx skills add loopdive/js2 --skill sprint-planning
Clone the repo
git clone --depth 1 https://github.com/loopdive/js2

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 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 $0.00030 $0.00736
Opus 5 $0.00015 $0.00368
Sonnet 5 $0.00006 $0.00147
Haiku 4.5 $0.00003 $0.00074

Measured 2d ago against content hash d60dce6a577e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-planning 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.

.claude/skills/sprint-planning/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sprint Planning

Facilitates sprint planning as a collaborative process. Can be run by the tech lead, PO, or any agent.

Participants

Planning should involve multiple perspectives. If dedicated agents are spawned, message them. If not, invoke the relevant skills inline:

  • PO perspective: prioritize by value, write acceptance criteria
  • Architect perspective: feasibility assessment, specs for hard issues (use /architect-spec)
  • SM perspective: process constraints from last retro, capacity limits
  • Dev perspective: estimate effort, flag risks

Step 1: Read current state

# Check baseline
cat plan/issues/{N-1}/sprint.md | grep "Final numbers"

# Check what's ready
rg -l '^status: ready$' plan/issues/*.md

# Check dependency graph
cat plan/log/dependency-graph.md

# Check last retro for process constraints
cat plan/issues/{N-1}/sprint.md | grep -A 3 "Action items"

Step 2: Validate candidate issues

For each high-priority issue, smoke-test against current main (use /smoke-test-issue):

  • Still fails: candidate for sprint
  • Already passes: close it, mark it done
  • Partially fixed: update issue with current status

Step 3: Prioritize by value

Order candidates by impact × unblocking potential, not just CE/FAIL count:

  • Which fixes unblock the most downstream work?
  • Which affect the most test categories?
  • Which are quick wins vs deep investigations?

Step 4: Assess feasibility

For each candidate:

  • Easy (< 50 lines, clear fix): dispatch directly to dev
  • Medium (< 150 lines, known approach): dispatch with guidance in task description
  • Hard (> 150 lines, unclear approach, core codegen): invoke /architect-spec first, dispatch only after spec is written

Step 5: Check capacity

  • Max 3 dev agents (16GB RAM constraint)
  • 1 task per dev at a time (wait for merge before next)
  • Account for merge/test cycle time (~10-15 min per task)
  • Typical sprint: 6-10 tasks across 2-3 devs

Step 6: Create task queue

Read the full file on GitHub · 91 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 First seen · 91 lines · 30 tokens per session scan A d60dce6a577e

Subscribe to this mod's changes

sprint-planning is a skill published in the GitHub repository loopdive/js2 (59 stars, last pushed 2d ago), licensed Apache-2.0. It adds 30 tokens to every session and 736 once invoked, about $0.0002 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.