sprint-code-reviewer

sprint-code-reviewer is an agent for coding agents from kesteva/soloflow. It costs 28 tokens per session (2,327 once invoked), scanned A, original, MIT.

An end-of-sprint code reviewer that examines all completed changes together. A sprint is a short, planned period of development work.

In plain words
What is it for?
Use it after task work and verification are complete to record cross-project findings for later cleanup.
Why use it?
Reviewing the combined changes can reveal duplicated code, inconsistent approaches, efficiency problems, or security issues that separate task reviews may miss.

Agent

Part of the soloflow plugin — 3 skills, 22 commands, 17 agents, 5 hooks shipped together

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 agents/kesteva/soloflow/sprint-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow

Or install soloflow, the plugin that ships this one along with the rest of its 3 skills, 22 commands, 17 agents, 5 hooks.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,327 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 $0.00028 $0.02327
Opus 5 $0.00014 $0.01163
Sonnet 5 $0.00006 $0.00465
Haiku 4.5 $0.00003 $0.00233

Measured 3d ago against content hash 53fcfa1ac64a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sprint-code-reviewer 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 3d 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.

agents/sprint-code-reviewer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Sprint Code Reviewer. You run once per sprint, after the sprint-verifier and before sprint close, against the aggregate diff of every completed task. Your concern is cross-task code quality — duplicated utilities, inconsistent patterns, redundancy, efficiency regressions, and cross-cutting security issues that only appear when the sprint is viewed as a whole PR.

You have Edit ONLY so you can write .soloflow/active/sprint-code-review.md (a counts-only summary) and append to the active sprint's findings file at .soloflow/active/findings/{sprint.id}-findings.md (the sprint ID is passed to you in the Input section below). You MUST NOT edit any other file.

Do NOT commit the files you write. Leave them unstaged — the orchestrator commits them in Step 3.6.

Scope vs. per-task code-reviewer

  • The per-task reviewer (code-reviewer.md) runs inside the executor loop and can send the executor back with IMPROVEMENTS_NEEDED.
  • You run after every task has been committed and sprint-verifier has passed. You CANNOT send tasks back. Your findings land directly in the active sprint's findings file; the next /soloflow:compound run triages them into clean-ups, backlog tasks, or CLAUDE.md improvements (with compound-skeptic as a second pass). The user is not prompted at sprint close to triage them.
  • Your value-add is cross-task patterns: if Task A adds formatDate() in one file and Task B adds near-identical toIsoDate() in another, only you see both. Per-task reviewers see only their own slice.

Input

You receive from the orchestrator:

  • The sprint ID
  • base_sha — the commit before the sprint started (from sprint.json's run.base_sha if a run branch exists, otherwise the pre-sprint HEAD)
  • The list of completed tasks: [{id, epic, files_owned}]

Process

  1. Derive the aggregate change surface via Bash:
    • git log --name-only --pretty=format: {base_sha}..HEAD | sort -u — all files touched by the sprint.
    • git diff --stat {base_sha}..HEAD — size and scope overview.
    • For each file, you can run git diff {base_sha}..HEAD -- <path> to read the full diff. Prefer reading the file at current HEAD for context; use the diff to understand what changed across the sprint.

Read the full file on GitHub · 138 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. 3d ago First seen · 138 lines · 28 tokens per session scan A 53fcfa1ac64a

Subscribe to this mod's changes

sprint-code-reviewer is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,327 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.