A command that takes ready tasks from a backlog and runs them through implementation, verification, and code review until the sprint is finished. A backlog is a list of planned work, and a sprint is a focused batch of tasks.

Use it to execute selected ready tasks, all eligible tasks, or tasks associated with a specific idea, with optional review and verification settings.

It removes the need to start each task and check its result manually, while still allowing verification and review to be switched on or off.

sprint — Command by kesteva

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/kesteva/soloflow/sprint

Clone the repo

git clone --depth 1 https://github.com/kesteva/soloflow

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 14,127 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.14127
Opus 5	$0.00005	$0.07064
Sonnet 5	$0.00002	$0.02825
Haiku 4.5	$0.00001	$0.01413

Measured 2d ago against content hash b3bf4f849fa7, 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.

commands/sprint.md · 700 lines

How it starts

The opening of the file, as written. The whole thing — 700 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:sprint

Phase 3 of the SoloFlow pipeline. Creates a sprint from ready tasks in the backlog and runs the executor → verifier → code-reviewer loop until the sprint is complete.

Arguments: $ARGUMENTS (optional — specific task IDs to include, or an IDEA-NNN to filter; if empty, include all ready tasks up to resolved limits.max_sprint_tasks). May also include review/verification flags — see Step 0.4.

Step 0.4: Parse flags

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/sprint/parse-flags.js" --args "$ARGUMENTS"

The script returns JSON { positional, flags, effective, summary_line }. Consume:

positional → effective $ARGUMENTS used by Step 1.5d and elsewhere.
effective.per_task_verification_enabled, per_task_code_review_enabled, sprint_verification_enabled, sprint_code_review_enabled → the four booleans used by downstream steps.
summary_line → print it (only if non-empty) so the user sees what's disabled.

If the script exits with code 2, stdout contains {"error": "..."}. Print the error message and stop — this is the fail-closed path for unknown flags like --no-codereview.

Recognized flags:

--quick — shorthand for --no-code-review --no-verification
--no-code-review — disables per-task (Step 3.f) and end-of-sprint (Step 3.6) code review
--no-verification — disables per-task (Step 3.d) and end-of-sprint (Step 3.5) verification

The flag layer sits on top of config resolution; the script already folds the resolved code_review.enabled and sprint_code_review.enabled config values into the returned booleans.

Model + limits resolution (applies throughout this command)

Run once at the start of the run and cache the result:

node "${CLAUDE_PLUGIN_ROOT}/scripts/config/resolve.js" --all

Use the resolved object for every Agent spawn's model parameter and wherever limits appear below. Keys consumed:

Model mapping (fallback matches the agent's frontmatter model:):

models.sprint_initiator / models.executor / models.test_writer / models.sprint_closer → sonnet
models.verifier / models.code_reviewer / models.sprint_verifier / models.sprint_code_reviewer → opus

Read the full file on GitHub · 700 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.

2d ago First seen · 700 lines · 0 tokens per session scan A b3bf4f849fa7

Subscribe to this mod's changes

sprint is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 14,127 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.

Code review Project management

sprint

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/soloflow:sprint

Step 0.4: Parse flags

Model + limits resolution (applies throughout this command)

What this file has done since we first saw it

Other commands, from other repositories

template

project-recap

speckit.taskstoissues

ado-pull

issue-amend

dispatch-worker