Agent skill

Sprint Plan

by borghei in borghei/Claude-Skills

Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises.

MITAuto-check passedProduct & Project Management

Install Sprint Plan

skills CLI
$ npx skills add borghei/Claude-Skills --skill sprint-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills sprint-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/project-management/execution/sprint-plan .claude/skills/sprint-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sprint-plan
GitHub stars
881
Token cost
~2k tokens
SKILL.md length
882 words
Files
5 (incl. scripts, references, assets)
Skills in repo
349
Repo updated
First seen
Licence
MIT

At a glance

Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises.

  • Works in 8 steps: Define the sprint goal → Calculate capacity → Pull from backlog → …
  • Build the sprint planning artifact itself
  • SKILL.md covers When to use this skill, The 7 sprint-plan elements, Clarify First and Workflow, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Sprint Plan is an agent skill from borghei/Claude-Skills. Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises. Use to build the sprint planning artifact itself.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/sprint_plan_template.md`, `references/capacity-math.md` and `references/sprint-anti-patterns.md`).

It sits in Product & Project Management, covering Sprint planning and agile. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • Build the sprint planning artifact itself
  • Tasks that involve Sprint planning and agile

Example prompts

  • “/sprint-plan”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Define the sprint goal
  2. Calculate capacity
  3. Pull from backlog
  4. Commit vs stretch
  5. Identify dependencies
  6. Identify risks
  7. Definition of done
  8. Run sprint_planner.py

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sprint Plan loads about 2k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 882 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 882 words, ~1,972 tokens.

Download SKILL.mdSave it as .claude/skills/sprint-plan/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
sprint-plan
description
Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises. Use to build the sprint planning artifact itself.
license
MIT + Commons Clause
metadata.version
1.0.0
metadata.author
borghei
metadata.category
project-management
metadata.domain
execution
metadata.updated
2026-05-27
metadata.python-tools
sprint_planner.py
metadata.tech-stack
sprint-planning, capacity, agile, story-points

Sprint Planning

A sprint plan that survives contact with reality. Covers capacity math, commit vs stretch separation, dependency identification, and the pre-sprint review that prevents mid-sprint surprises.

When to use this skill

  • Sprint kickoff (every 1-3 weeks)
  • Sprint-plan template for new teams
  • Sprint-plan audit when sprints consistently miss
  • Quarter-start planning (rolled up across sprints)
  • Post-mortem on a missed sprint (gap analysis)

The 7 sprint-plan elements

  1. Sprint goal — one sentence: what this sprint exists to achieve
  2. Team capacity — actual hours / story points after PTO, on-call, etc.
  3. Commits — items the team confidently ships
  4. Stretch — items if everything goes well; nothing depends on
  5. Dependencies — what must happen by when (external + internal)
  6. Risks — what could derail; mitigation per risk
  7. Definition of done — when is each item "done"?

Clarify First

Before generating the sprint plan, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Sprint goal — the one-sentence outcome this sprint exists to achieve (element 1; lets you scope and say no to off-goal asks)
  • Real team capacity — working days minus PTO/on-call/meetings/interrupts × focus factor (element 2; sizes the commit and prevents the 100%-fill miss)
  • Backlog readiness — are candidate items refined, estimated, and ≤5 days (unrefined items are ineligible and blow estimates mid-sprint)
  • Known dependencies — cross-team/external blockers with owners (element 5; unconfirmed assumptions become mid-sprint crises)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Workflow

Step 1 — Define the sprint goal

A good goal:

  • One sentence
  • States outcome, not output ("ship 3 features" → "complete checkout flow MVP enabling first paid customers")
  • Inspires the team
  • Lets you say "no" to off-goal asks
Step 2 — Calculate capacity

Per team member:

  • Working days = sprint days - holidays - approved PTO
  • Effective hours = days × hours/day × focus factor (typically 0.6-0.75)
  • Subtract on-call rotation hours
  • Subtract meeting overhead
  • Subtract support / interrupt tax

Aggregate across team. This is your real capacity.

Step 3 — Pull from backlog

Backlog items must be:

  • Refined (acceptance criteria clear)
  • Estimated (story points or hours)
  • No major unknowns

Items that fail this are NOT eligible for the sprint. Send back to refinement.

Step 4 — Commit vs stretch
  • Commits: 75-85% of capacity (leaves room for unknowns)
  • Stretch: 10-15% of capacity (only if commits done)

Stuffing 100% of capacity = guaranteed miss. Reality always intrudes.

Step 5 — Identify dependencies

For each item:

  • Cross-team dependencies (what they need from others)
  • External dependencies (vendors, customers)
  • Sequencing dependencies (A blocks B)

Each dependency needs:

  • Owner
  • Date needed by
  • Confirmation it's planned
Step 6 — Identify risks

For each item, list likely risks:

  • Technical risk
  • Dependency risk (external owner slips)
  • Estimate risk (unknowns might double effort)
  • Capacity risk (key person may be pulled)

Per risk: likelihood, severity, mitigation, owner.

Step 7 — Definition of done

Per item:

  • Code merged + reviewed
  • Tests added
  • Telemetry firing
  • Docs updated
  • Accessibility checked
  • Feature flag configured (if applicable)
  • QA passed
Step 8 — Run sprint_planner.py

Audit capacity utilization, commit/stretch split, dependency clarity, DoD coverage.

bash
python3 project-management/execution/sprint-plan/scripts/sprint_planner.py \
  --input sprint_plan.json --format markdown

Decision frameworks

Capacity math (per 2-week sprint, 8-person team)
2 weeks = 10 working days
Per person:
  - 10 days × 8 hours = 80 hours raw
  - Minus PTO/holidays (e.g., 1 day) = 72 hours
  - Minus meetings (~10 hrs) = 62 hours
  - Minus on-call (~4 hrs avg) = 58 hours
  - Minus interrupts/support (~6 hrs) = 52 hours
  - Focus factor 0.7 = ~36 hours of "real" work

Team of 8 × 36 hours = 288 effective hours
                     = ~28 person-days of real engineering work

Most teams over-estimate capacity by 30-50%. Track actuals to calibrate.

Show full SKILL.md (363 more words)Show less
Commitment discipline
Filled atOutcome
100%+Always miss
90-100%Usually miss; no room for unknowns
80-90%Often achievable; healthy
70-80%Conservative; safer commits
< 70%Under-committing; team disengaged

Target: 80% commits + 15% stretch.

Sprint goal vs feature list
Sprint goalWhy better
"Complete checkout MVP"Outcome-aligned; defines what "done" looks like
"Ship feature X + Y + Z"Feature list; what if one slips?
"Improve performance"Vague; no done state

A good sprint goal lets you say "we did it" or "we didn't" clearly.

Item sizing

Stories should be 1-5 days each. Stories > 5 days:

  • Split into smaller stories
  • Add a planning task to break them down
  • Don't commit until refined
When to descope vs add capacity

Mid-sprint, when you realize commit is too much:

  • Descope: drop a stretch item; cleanly remove from sprint
  • Add capacity: rare; usually means borrowing from next sprint
  • Push: absolute last resort; deal carefully with stakeholders

Discipline: descope early. Heroic late nights = burnout + bugs.

Common engagements

"Plan our next sprint"
  1. Pull team's velocity history (last 3-5 sprints).
  2. Calculate this sprint's capacity.
  3. Choose sprint goal aligned with quarter OKRs.
  4. Pull from backlog; verify items refined.
  5. Commit to 80%; stretch 15%.
  6. Identify dependencies + risks.
  7. Define done per item.
"Why are we missing every sprint?"
  1. Audit last 3 sprint plans + actuals.
  2. Diagnose: over-commit? estimation? unrefined items? interrupts?
  3. Tighten capacity math.
  4. Increase refinement discipline.
  5. Track interrupts; reduce them.
"Quarter planning rolled up from sprints"
  1. Define quarter goal (themes).
  2. Identify ~6 sprints of capacity.
  3. Allocate to: themes, tech debt, support, OKRs.
  4. Draft per-sprint goals.
  5. Refresh per sprint planning meeting.

Anti-patterns to avoid

  • 100% capacity commit. Always miss.
  • Mid-sprint scope add without descope. Burnout + bugs.
  • No sprint goal. Random feature list.
  • Unrefined items committed. Discovered complexity blows estimates.
  • Dependency assumption without owner confirmation. Slips.
  • No risk identification. Risks surface as crises.
  • No DoD. "Done" varies by person.
  • Velocity ignored. Repeat estimation mistakes.

References

  • references/capacity-math.md — deep on per-person capacity, focus factor, interrupt tax
  • references/sprint-anti-patterns.md — common failures + fixes
  • project-management/scrum-master — process facilitation
  • project-management/execution/backlog-refinement — pre-sprint item prep
  • project-management/execution/story-splitting — sizing large stories
  • project-management/execution/cycle-time-analyzer — velocity tracking
  • project-management/sprint-retrospective — post-sprint learning
  • c-level-advisor/vpe-advisor — capacity planning at scale

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in project-management/execution/sprint-plan of borghei/Claude-Skills.

  • SKILL.md
  • assets/sprint_plan_template.md
  • references/capacity-math.md
  • references/sprint-anti-patterns.md
  • scripts/sprint_planner.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Sprint Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sprint Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sprint Plan this skillborghei/Claude-Skills881—~2kAutomated safety check: PassMIT
Convex Create Componentspokvulcan/poker-planning1148 repos~2.6kAutomated safety check: PassMIT
Convex Migration Helperspokvulcan/poker-planning1148 repos~1.4kAutomated safety check: PassMIT
Agile Product Owneralirezarezvani/claude-skills28k3 repos~3.2kAutomated safety check: PassMIT
Convex Performance Auditspokvulcan/poker-planning1147 repos~1.9kAutomated safety check: PassMIT
Walking Skeleton Roadmap Scopingprime-radiant-inc/iterative-development181—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Convex Create Component

    spokvulcan/poker-planning

    Builds reusable Convex components with isolated tables and app-facing APIs.

    114 GitHub starsUsed in 8 repos~2.6k tokens
    Product & Project ManagementAuto-check passed
  • Convex Migration Helper

    spokvulcan/poker-planning

    Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations.

    114 GitHub starsUsed in 8 repos~1.4k tokens
    Product & Project ManagementAuto-check passed
  • Agile Product Owner

    alirezarezvani/claude-skills

    Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.

    28k GitHub starsUsed in 3 repos~3.2k tokens
    Product & Project ManagementAuto-check passed
  • Convex Performance Audit

    spokvulcan/poker-planning

    Audits Convex performance for reads, subscriptions, write contention, and function limits.

    114 GitHub starsUsed in 7 repos~1.9k tokens
    Product & Project ManagementAuto-check passed
  • Walking Skeleton Roadmap Scoping

    prime-radiant-inc/iterative-development

    Turns extracted requirements into a roadmap by choosing a walking skeleton iteration with its first journey scenario and ordering the remaining work into follow-on iterations.

    181 GitHub stars~1.7k tokensUpdated 4 mo ago
    Product & Project ManagementAuto-check passed
  • Convex

    spokvulcan/poker-planning

    Routes general Convex requests to the right project skill. An agent skill from spokvulcan/poker-planning.

    114 GitHub starsUsed in 6 repos~399 tokens
    Product & Project ManagementAuto-check passed

More from borghei/Claude-Skills

All 349 skills in this repo
  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    881 GitHub stars~4.2k tokensUpdated yesterday
    Auto-check passed
  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    881 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    881 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    881 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    881 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Brainstorm Okrs

    borghei/Claude-Skills

    OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.

    881 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Sprint Plan

What does Sprint Plan do?

Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises. Sprint Plan is an agent skill from borghei/Claude-Skills. Plan a sprint that ships — capacity, commitment vs stretch, dependencies, and risk identification that prevents mid-sprint surprises.

When should I use Sprint Plan?

Sprint Plan fits situations like: build the sprint planning artifact itself; tasks that involve Sprint planning and agile.

How do I install Sprint Plan in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill sprint-plan -a claude-code`. Or copy the skill folder (project-management/execution/sprint-plan in borghei/Claude-Skills) into .claude/skills/sprint-plan in your project. Claude Code loads it when a task matches its description.

How do I install Sprint Plan in Codex?

Run `npx skills add borghei/Claude-Skills --skill sprint-plan -a codex`. Or copy the skill folder (project-management/execution/sprint-plan in borghei/Claude-Skills) into .agents/skills/sprint-plan in your project. Codex loads it when a task matches its description.

Can I use Sprint Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill sprint-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sprint-plan, .gemini/skills/sprint-plan, .github/skills/sprint-plan and .opencode/skills/sprint-plan in your project.

What does Sprint Plan need to run?

Going by SKILL.md and its folder, Sprint Plan needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Sprint Plan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sprint Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sprint Plan use?

Sprint Plan is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sprint Plan use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.

What are the alternatives to Sprint Plan?

Skills that share tags, products or a category with Sprint Plan: Convex Create Component (spokvulcan/poker-planning, 114 stars), Convex Migration Helper (spokvulcan/poker-planning, 114 stars), Agile Product Owner (alirezarezvani/claude-skills, 28k stars) and Convex Performance Audit (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sprint Plan?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.