What is review-conventions?

A checklist for reviewing code changes in this project, with attention to security, correctness, conventions, and verification. It includes checks for path traversal, API requests, validation, errors, and destructive operations.

Use it to review pull requests or diffs, check security and tool implementations, and run the project's verification commands.

It helps catch unsafe inputs, incorrect API behavior, leaked error details, and missing project conventions before code is committed.

How pingidentity/aic-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pingidentity/aic-mcp-server. 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/pingidentity/aic-mcp-server/main/.claude/skills/review-conventions/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/pingidentity/aic-mcp-server

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/pingidentity/aic-mcp-server/review-conventions/github.svg)](https://agentmods.dev/skills/pingidentity/aic-mcp-server/review-conventions)

Your own site

<a href="https://agentmods.dev/skills/pingidentity/aic-mcp-server/review-conventions"><img src="https://agentmods.dev/badge/skills/pingidentity/aic-mcp-server/review-conventions/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/pingidentity/aic-mcp-server/review-conventions"><img src="https://agentmods.dev/badge/skills/pingidentity/aic-mcp-server/review-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 732 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	$0.00062	$0.00732
Opus 5	$0.00031	$0.00366
Sonnet 5	$0.00012	$0.00146
Haiku 4.5	$0.00006	$0.00073

Measured 9d ago against content hash ec39c2852e31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-conventions 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 9d 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-conventions/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Conventions

Priority Order

Security — path traversal, scope correctness, error message leakage
Correctness — API contract, response formatting, error handling
Conventions — helper usage, naming, annotations, test structure
Quality — readability, duplication, edge cases

Tool Implementation Checklist

SCOPES defined as module-level const and passed to both the tool object and makeAuthenticatedRequest()
All user-provided path segments validated with safePathSegmentSchema
Uses makeAuthenticatedRequest() for API calls, never raw fetch
Returns via createToolResponse(), success responses use formatSuccess(data, response) to include transaction ID
Error handling: catch (error: any) returning createToolResponse('Failed to ...: ${error.message}')
Realm parameters use z.enum(REALMS) from validationHelpers
Export name follows <toolName>Tool convention
DELETE operations have annotations: { destructiveHint: true }
Idempotent PUT/PATCH operations have annotations: { idempotentHint: true }

Common Pitfalls

Pitfall	What to look for
Missing path traversal protection	Any ID parameter in a URL path not using `safePathSegmentSchema`
Missing destructiveHint	DELETE or destructive operations without `annotations: { destructiveHint: true }`
Hardcoded scopes	Scopes written inline in `makeAuthenticatedRequest()` instead of referencing the `SCOPES` const
Raw JSON response	Returning `JSON.stringify(data)` without `formatSuccess()` — loses transaction ID
Theme data loss	Theme update/delete operations that don't preserve `isDefault` or other realm data
AM helper bypass	AM tools not using `buildAMRealmUrl()` and `AM_API_HEADERS` from `amHelpers`

Read the full file on GitHub · 61 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.

9d ago First seen · 61 lines · 62 tokens per session scan A ec39c2852e31

Subscribe to this mod's changes

review-conventions is a skill published in the GitHub repository pingidentity/aic-mcp-server (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 732 once invoked, about $0.0003 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 2026-08-31.

Code review Security

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

aic-mcp-server: Skill for Claude Code