agentmods.dev

swe-review

swe-review is a skill for Claude Code from SNIKO/agent-skills. It costs 45 tokens per session (839 once invoked), scanned A, original, MIT.

A code and software-work document review step that examines plans, specifications, progress notes, research reports, code changes, branches, or pull requests using fresh context.

In plain words
What is it for?
Use it to review SWE artifacts or code changes independently before deciding the next engineering action.
Why use it?
It helps catch confirmed, actionable problems without relying on the reviewer’s memory of how the work was produced. The findings support a decision about whether to revise, go back to an earlier stage, or continue.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

not rated 2repo 2mo ago A scan 45 tokens original MIT

Good fit Use it to review SWE artifacts or code changes independently before deciding the next engineering action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sniko/agent-skills/swe-review
View source ↗ SNIKO/agent-skills
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 SNIKO/agent-skills --skill swe-review
Clone the repo
git clone --depth 1 https://github.com/SNIKO/agent-skills

Made for: Claude Code.

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 swe-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sniko/agent-skills/swe-review"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/swe-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 839 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 $0.00045 $0.00839
Opus 5.5 $0.00018 $0.00336
Sonnet 5.5 $0.00009 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured 1mo ago against content hash 76f4d295d1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swe-review 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 1mo 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.

skills/swe-review/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline

swe-shape → swe-spec → [swe-plan] → [swe-worktree] → swe-execute → swe-review, with swe-research available at any point.

Each stage runs in its own session — that separation is what makes this review independent. Assume no memory of the session that produced the target.

  • This stage: review one artifact or one code change with fresh context.
  • Reads: the review target, its upstream artifacts, and the repository. Artifacts are brief.md (problem and acceptance, from swe-shape), spec.html (design and contracts, from swe-spec), plan.md (slice ordering, from swe-plan), state.md (execution progress, from swe-execute), and research reports (from swe-research).
  • Writes: nothing. Findings are returned in chat.
  • Next: the user decides whether to revise, return upstream, or proceed.

Purpose

Provide an independent, concise review of either an SWE artifact or changed code. Optimize for confirmed, actionable findings rather than volume.

Modes

Choose exactly one mode from the user's target:

  • Artifact review: brief.md, spec.html, plan.md, state.md, or a research report.md.
  • Code review: pull request, branch, commit range, staged changes, unstaged changes, or an implementation checked against SWE artifacts.

When the target is ambiguous and artifact and code review would produce materially different scopes, ask one clarifying question. Otherwise infer the mode from the path or request.

Workflow

  1. Identify the exact review target and scope.
  2. Read the corresponding reference completely:
  3. Apply repository rules before general review preferences.
  4. Treat the target as if entering with fresh context: verify its claims and do not defend decisions because they appeared earlier in the conversation.
  5. Return only verified, deduplicated, actionable findings in the reference's output format.

Read the full file on GitHub · 69 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 69 lines · 45 tokens per session scan A 76f4d295d1eb

Subscribe to this mod's changes

swe-review is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 839 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Code reviewagentsanthropicclaudecodecodexcopilot-cliopenai
Related

Other skills, from other repositories

oracle

Oracle second-model review: bundle prompts/files, debug, refactor, design.

steipete/oracle · 18 tokens

pr-screenshot-comparison

Create clear, polished before-and-after screenshots from the actual running product for a GitHub pull request. Use when a UI change needs visual proof: capture matching product states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the…

petekp/claude-code-setup · 70 tokens

pr-description

Write or update a GitHub PR description a teammate understands in one quick read: clear before/after behavior, useful visual evidence, and plain sentences grounded in the diff and real verification. Use when opening a PR or editing its description.

petekp/claude-code-setup · 50 tokens

pr-self-review

Draft explanatory author-context comments for the user's own PR or local diff. Use for self-review or reviewer context, not a formal review submission. Posting requires approval.

petekp/claude-code-setup · 36 tokens

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.

langchain-ai/open-swe · 52 tokens

workspaces

How an Open SWE workspace's sandbox image works and how to change it — create one, edit or fork an existing one, start from scratch, what setupscript and updatescript are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in progress. Read this whenever someone asks about…

langchain-ai/open-swe · 89 tokens