A code-review procedure for checking a branch, code difference, or pull request before it is merged. A pull request is a proposed change for others to inspect and accept.

It helps review changes against the base branch, trace serious findings to their causes, and perform a final self-review before opening or approving a pull request.

It focuses reviews on defects that matter, rather than style comments or problems automated checks would already find. It also checks surrounding code, callers, tests, compatibility, security, documentation, and release details.

How SalesforceCommerceCloud/b2c-developer-tooling configures Claude Co

Reuse

Borrowing it

Nothing to install: this file belongs to SalesforceCommerceCloud/b2c-developer-tooling. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SalesforceCommerceCloud/b2c-developer-tooling/main/.claude/skills/review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/SalesforceCommerceCloud/b2c-developer-tooling

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/review/github.svg)](https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/review)

Your own site

<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/review"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/salesforcecommercecloud/b2c-developer-tooling/review"><img src="https://agentmods.dev/badge/skills/salesforcecommercecloud/b2c-developer-tooling/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,125 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.01125
Opus 5.5	$0.00023	$0.00450
Sonnet 5.5	$0.00012	$0.00225
Haiku 4.5	$0.00006	$0.00112

Measured 4d ago against content hash 0097ec817ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 4d 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.

.claude/skills/review/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review

This skill covers reviewing changes to this monorepo, whether that is your own work before a PR or someone else's PR.

Scope

Review the net change against the base branch (git diff main...HEAD, or gh pr diff <number>), not individual commits.
Read the surrounding code, callers, and tests, not only the changed lines. Many defects come from what the diff fails to update.
Lint, prettier, typecheck, and the copyright header are enforced by CI. Do not report anything those tools would catch. If you have not run them, say so.

Signal Over Noise

A short list of findings that matter is more useful than a long list of observations. Report something only if a maintainer would want it changed before merge, or would want to know about it before release. Leave out style preferences, naming opinions that are not misleading, and hypothetical problems with no realistic path to happen.

Verify Before Reporting

For each serious finding:

Trace the path that triggers it: the caller, the inputs, and the resulting behavior.
Check whether the behavior is intentional. Look at code comments, tests that assert it, docs, and the PR description.
If you cannot confirm it, lower its severity or present it as a question.
Code elsewhere in the repo doing the same thing does not make a bug acceptable. Mention when the same problem exists elsewhere.

Severity

Blocker: wrong behavior, data loss, security exposure, an unmarked breaking change, or a broken release or CI.
Should fix: a real defect or gap with limited impact, such as a missing test for changed behavior, a missing changeset or docs update, or an inconsistency across surfaces.
Consider: a worthwhile improvement that does not need to block merge.

What to Check

Correctness and errors

Failures must not be reported as success or as empty results. A refused request should not become "no items found" with exit code 0.
API errors should destructure response and use getApiErrorMessage(error, response).
Flags that duplicate configuration (site ID, realm, MRT project, ...) must fall back to configuration via flagOrConfig. See the CLI command development skill.

Read the full file on GitHub · 83 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.

4d ago Changed · +1 lines 0097ec817ffe
16d ago First seen · 82 lines · 58 tokens per session scan A cd4028c23bb3

Subscribe to this mod's changes

review is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (58 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,125 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 2026-10-22.

Code review Commits Git and workflow b2c cli dx

review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewSalesforceCommerceCloud/b2c-developer-tooling	Skill	58	yesterday	Apache-2.0	A	58	Claude Code
autofix-prQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	141	Claude Code
git-irishyperb1iss/git-iris	Skill	43	3d ago	Apache-2.0	A	81	Claude Code, Codex
loop-gh-prrestarter/lets-workflow	Skill	17	3d ago	MIT	A	118	Claude Code
requesting-code-reviewaxiomantic/spellbook	Skill	11	2d ago	MIT	A	77	Claude Code, Codex
fixJebel-Quant/rhiza-claude	Skill	6	3d ago	none	A	51	Claude Code
gitdean0x/devflow	Skill	21	yesterday	MIT	C	36	Claude Code

b2c-developer-tooling: Skill for Claude Code