review-sprint

review-sprint is a skill for Claude Code from atman-33/workhub. It costs 43 tokens per session (332 once invoked), scanned A, original, MIT.

A sprint review writer that compares planned work with completed work using project records and merge history. It records the sprint goal result, delivered items, unfinished items, metrics, and carry-over decisions.

In plain words
What is it for?
Use it when closing a sprint or preparing a sprint summary. It helps document what shipped, what did not, how many points were completed, and where remaining items go.
Why use it?
It replaces memory-based summaries with evidence from the backlog, code merges, and progress history. It also keeps unfinished work’s next step explicit without deciding for the team.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the team-ops plugin — 13 skills shipped together

Good fit Use it when closing a sprint or preparing a sprint summary. It helps document what shipped, what did not, how many points were completed, and where remaining items go.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atman-33/workhub/review-sprint
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.

Any agent
npx skills add atman-33/workhub --skill review-sprint
Clone the repo
git clone --depth 1 https://github.com/atman-33/workhub

Made for: Claude Code.

Or install team-ops, the plugin that ships this one along with the rest of its 13 skills.

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 review-sprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/atman-33/workhub/review-sprint/github.svg)](https://agentmods.dev/skills/atman-33/workhub/review-sprint)
Your own site
<a href="https://agentmods.dev/skills/atman-33/workhub/review-sprint"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/review-sprint/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.

agentmods 80×15 button for review-sprint

Your own site · 80×15
<a href="https://agentmods.dev/skills/atman-33/workhub/review-sprint"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/review-sprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.00332
Opus 5 $0.00022 $0.00166
Sonnet 5 $0.00009 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 6d ago against content hash b6b65a41d857, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-sprint 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 6d 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/team-ops/skills/review-sprint/SKILL.md · 31 lines

What it actually says

Review a sprint

Summarize what the sprint actually delivered, anchored on data — not memory.

Steps

  1. Resolve the sprint (default: latest sprints/<id>/ with a scope.json).
  2. Gather facts:
    • scope.json vs each item's current status → done / not-done split
    • repos/<repo>/pbi-activity.json → what was actually merged per PBI
    • backlog/progress-history.jsonl → points burned over the sprint
  3. Write sprints/<id>/review.md (team content language):
    • Sprint goal: met / partially / missed, with one-line evidence
    • Done items (with merge evidence and demo pointers where the PBI notes have them); not-done items with why
    • Metrics: committed vs completed points, velocity trend
    • Carry-over: agree with the user per unfinished item — back to backlog (clear sprint:) or into the next sprint (plan-sprint handles that)
  4. Update the affected PBI files/backlog table per the carry-over decision, and append an activity-log line.

Rules

  • Marking items done is the humans' call during the review — record what they decide, don't decide for them.
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. 6d ago First seen · 31 lines · 43 tokens per session scan A b6b65a41d857

Subscribe to this mod's changes

review-sprint is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 332 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 2026-09-03.