sprint

A way to manage one focused batch of planned work at a time, with a stated goal, selected stories, and recorded unfinished work.

In plain words
What is it for?
Open a sprint, commit backlog stories, check their status, return unfinished stories with reasons, and close only when every story is done or carried over.
Why use it?
It keeps the team from quietly carrying incomplete tasks forward or claiming progress before the work is accounted for.

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/azrtydxb/procoder/sprint
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 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 $0.00026 $0.00427
Opus 5 $0.00013 $0.00214
Sonnet 5 $0.00005 $0.00085
Haiku 4.5 $0.00003 $0.00043

Measured 2d ago against content hash 3bbac814e711, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.kilo/commands/sprint.md · 36 lines

What it actually says

The user invoked /procoder:sprint with arguments: $ARGUMENTS

The command below is the procoder binary on PATH.

A sprint is a commitment, not a calendar: a goal plus the stories pulled into it, opened and closed explicitly. One sprint is active at a time — that is the WIP limit, and the point.

  • procoder sprint open <goal> — refuses while a sprint is active; otherwise prints the sprint file for you to write. State a real goal: what this sprint delivers, not a date range.
  • procoder sprint pull <story-id>... — commit stories to the active sprint. Done, missing, or already-committed stories are refused individually; the rest still pull.
  • procoder sprint status — goal, committed stories with statuses, done/total and carried counts. Run it before claiming progress.
  • procoder sprint carry <story-id> <reason> — return an unfinished story to the backlog, with the reason recorded in the story file. Lean makes unfinished work visible; carrying without a reason is refused.
  • procoder sprint close — REFUSES while a committed story is neither done nor carried. Finish it (backlog close story <id>) or carry it with a reason, then close; the sprint file gets a Result section with committed/done/carried counts and a Retro scaffold.
  • Fill the Retro before moving on — what slowed us, what we change, one adaptation worth keeping. The retro is the price of the next sprint: sprint open refuses while the last one's Retro is empty ([sprint] retro = "off" opts a repo out).

With arguments, run the matching subcommand and act on its output. Without arguments, run status and report where the sprint stands.

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 · 36 lines · 26 tokens per session scan A 3bbac814e711

Subscribe to this mod's changes

sprint is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 427 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 2026-08-30.