post-sprint

post-sprint is a command for coding agents from srbryers/slope. It costs 0 tokens per session (722 once invoked), scanned A, original, MIT.

A command for closing out a Slope development sprint. It creates and checks a scorecard, generates a review, and distills recurring problems from the work completed.

In plain words
What is it for?
Use it to determine the sprint, inspect its plan and commits, classify each ticket's result and hazards, build the scorecard, validate it, and produce review notes.
Why use it?
It turns scattered commits and notes into a consistent record, making it easier to see what worked, what failed, and what should change next time.

Command

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 commands/srbryers/slope/post-sprint
Clone the repo
git clone --depth 1 https://github.com/srbryers/slope

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 post-sprint

README.md
[![agentmods](https://agentmods.dev/badge/commands/srbryers/slope/post-sprint.svg)](https://agentmods.dev/commands/srbryers/slope/post-sprint)
Your own site
<a href="https://agentmods.dev/commands/srbryers/slope/post-sprint"><img src="https://agentmods.dev/badge/commands/srbryers/slope/post-sprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 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 $0.00000 $0.00722
Opus 5 $0.00000 $0.00361
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured 5d ago against content hash 72f4ea98ec97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

post-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 5d 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.

templates/claude-code/commands/post-sprint.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-Sprint — Scorecard, Review, Distill

Run the complete post-sprint routine. This automates scorecard creation, validation, review generation, and common-issues distillation.

Steps

1. Determine sprint number and gather context

  • Run slope next to get the current sprint number, or check for an active sprint with slope sprint status
  • Run git log --oneline to see all commits in the current sprint (since branching from main)
  • Read the sprint plan if one exists in .claude/plans/ or docs/backlog/

2. Build the scorecard

For each ticket/commit in this sprint, classify the shot:

  • Ticket key: Extract from commit messages (e.g., S21-1)
  • Title: Brief description of what was done
  • Club: driver (risky/new), long_iron (multi-package), short_iron (standard), wedge (small), putter (trivial)
  • Result: fairway, green, in_the_hole, or miss direction (long/short/left/right)
  • Hazards: Any gotchas encountered (check commit messages and PR comments for clues)
  • Notes: Key implementation details

Use the SLOPE MCP execute tool to build the scorecard programmatically:

const scorecard = buildScorecard({
  sprint_number: N,
  theme: "Sprint theme from plan",
  par: computePar(ticketCount),
  slope: computeSlope(slopeFactors),
  date: new Date().toISOString().split('T')[0],
  shots: [/* classified shots */]
});
return JSON.stringify(scorecard, null, 2);

Write the scorecard to docs/retros/sprint-N.json.

3. Validate

Run slope validate to check the scorecard for errors and warnings. Fix any issues.

4. Generate review

Run slope review to generate the sprint review markdown. Share the output with the user.

5. Distill learnings

If any new recurring patterns were encountered during this sprint:

  • Check .slope/common-issues.json for existing patterns
  • Add new patterns or update sprints_hit arrays for existing ones
  • Sweep for recurring workarounds that were routed around in-flow. Log structural ones with slope review findings add --type=workaround --recurs --cost=s|m|l --description="...".

Read the full file on GitHub · 70 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. 5d ago First seen · 70 lines · 0 tokens per session scan A 72f4ea98ec97

Subscribe to this mod's changes

post-sprint is a command published in the GitHub repository srbryers/slope (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 722 tokens. 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.