A set of instructions for reviewing existing code for design flaws, logic errors, security risks, and architecture problems before it is merged. A pull request is a proposed code change waiting for review.

Use it to review code or a pull request. It sets a review mode, examines the change in context, and reports issues with suggested fixes.

It provides a consistent review process and keeps an evaluation separate from making edits unless fixing was explicitly requested.

review-code — Skill by hellotern

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 skills/hellotern/sextant/review-code

Any agent

npx skills add hellotern/Sextant --skill review-code

Clone the repo

git clone --depth 1 https://github.com/hellotern/Sextant

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,538 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	$0.00119	$0.02538
Opus 5	$0.00060	$0.01269
Sonnet 5	$0.00024	$0.00508
Haiku 4.5	$0.00012	$0.00254

Measured 2d ago against content hash 7e631efcc94e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-code 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.

skills/review-code/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!../principles/SKILL_BODY.md

!../tool-gitnexus/SKILL_BODY.md

Code Review Workflow

Core Principle

The goal of code review is not to find fault, but to discover design flaws, logic vulnerabilities, and architecture risks before code is merged. Review quality depends on the reviewer's depth of understanding of the change context — the deeper the understanding, the more fundamental the issues found.

Before You Start

Operating Mode — Declare Before Starting

Before reading a single line of code, output this declaration as the first line of your response:

Mode: Review-only  — reason: <one phrase>

Mode: Review+patch — reason: <one phrase>

Mode selection rules:

Signal	Mode
"review this PR/code", user submitted code for evaluation	Review-only
"review and fix", "find and fix issues", you wrote the code	Review+patch
Ambiguous	Review-only — declare it and ask at the end if fixes are wanted

Review-only constraints (hard rules, not guidelines):

Do NOT call any Edit/Write/file-modification tool during this session.
If you feel compelled to fix something, add it to [Must Fix] with a suggestion instead.
Exception: user explicitly upgrades to Review+patch mid-session ("go ahead and fix it") — before making any changes, output: Mode upgrade: Review-only → Review+patch and then proceed.

Review+patch constraints:

Complete the full review output first. Do not patch silently.
Apply only Must Fix items after the review block is complete.
Suggested Improvements and Confirm Items remain output-only — no unilateral patch.

Reviewer Role

You are a gatekeeper, not a rewriter — point out problems and risks; don't rewrite the author's code (Review-only mode)
You are a second pair of eyes, not a style police — focus on logic correctness and architecture compliance; leave style to the linter
You are a collaborator, not a judge — give specific improvement suggestions, not abstract negations

Read the full file on GitHub · 245 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 · 245 lines · 119 tokens per session scan A 7e631efcc94e

Subscribe to this mod's changes

review-code is a skill published in the GitHub repository hellotern/Sextant (15 stars, last pushed 4mo ago), licensed MIT. It adds 119 tokens to every session and 2,538 once invoked, about $0.0006 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 Git and workflow Security agent-skills claude-code skill-md

review-code

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Code Review Workflow

Core Principle

Before You Start

Operating Mode — Declare Before Starting

Reviewer Role

What this file has done since we first saw it

Other skills, from other repositories

skill-authoring

iflytek-hyper-tts

iflytek-pdf-image-ocr

vastai-sdk

iflytek-text-proofread

iflytek-translate