A staged review workflow for a working tree, branch difference, pull request, or plan before it reaches the main branch. It gathers checks across areas such as specification, code quality, security, performance, and documentation, then reports findings and their root causes.

Use it to review code changes, pull requests, plans, and Markdown artifacts before merge.

It gives a change a structured review before it lands and surfaces risks that a single pass might miss. It reports findings without editing the reviewed work or repeatedly fixing it.

hex-review — Skill for Claude Code by grimoire-rs/grimoire

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 grimoire-rs/grimoire --skill hex-review

Clone the repo

git clone --depth 1 https://github.com/grimoire-rs/grimoire

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/grimoire-rs/grimoire/hex-review/github.svg)](https://agentmods.dev/skills/grimoire-rs/grimoire/hex-review)

Your own site

<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/hex-review"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-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/grimoire-rs/grimoire/hex-review"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,597 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	$0.00189	$0.07597
Opus 5.5	$0.00076	$0.03039
Sonnet 5.5	$0.00038	$0.01519
Haiku 4.5	$0.00019	$0.00760

Measured 1mo ago against content hash e8969fe84663, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hex-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.

.agents/skills/hex-review/SKILL.md · 553 lines

How it starts

The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hex-review — Adversarial Reviewer

Thin dispatcher. It resolves the review target and baseline, classifies the diff's tier, resolves overlays, runs the single meta-plan approval gate, announces the resolved config, and hands off to the matching tier file. hex-review never edits its own output or loops on it — the reviewer panel runs once per invocation and reports; applying the findings is /hex-execute's job. The phase plans live in the five tier-<tier>.md files; the shared vocabulary (tiers, worker roles, model classes, the memory file) lives in the hex-core reference library and is linked here, never copied.

Loop mode — the caller is /hex-execute or /hex-loop, not a human. It runs autonomously: no gate prompt, no question, ever (step 5). The report and the findings go back to the caller.

Shared contracts: protocol.md · workers.md · models.md · memory.md. If hex-core is not installed: grim add ghcr.io/michael-herwig/arcana/hex-core:latest.

Argument syntax

/hex-review [tier] <target> [flags]

tier (optional): low | medium | high | xhigh | max | auto. Default auto — the classifier picks low … xhigh from diff metrics. max is explicit only — --tier=max, or a plan whose Status block says Tier: max; the classifier never emits it (protocol.md).
target (one of):
- empty — in loop mode, anchor..HEAD (the plan's Reviewed: anchor when valid, else the resolved baseline; step 2). Otherwise the working tree: uncommitted changes (staged + unstaged) against HEAD. If the working tree is clean, fall back to the current branch's diff against the resolved baseline and say so in the announce block.
- a branch name — diffed against the resolved baseline.
- <N> / #<N> / PR <N> / pull/<N> / a full GitHub PR URL — an explicit pull request.
- a path to a markdown plan, ADR, or spec artifact — review the file directly, not a code diff. Diff metrics do not apply; see classify.md.
flags (before the target, by convention):
- --base=<git-ref> — the diff baseline. Pipeline input, not an overlay axis: everything downstream (metrics, tier, review scope, adversary scope) reads from it. Default resolution in step 2.
- --breadth=minimal|full|adversarial — override the Stage 2 panel breadth (see overlays.md).
- --rca=on|off — override root-cause (Five Whys) analysis.
- --adversary / --no-adversary — force the cross-model pass on or off.
- --dry-run — make the meta-plan gate block for explicit approval and stop there (preview only, no workers launched).

Read the full file on GitHub · 553 lines

Files

What ships with it

7 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.

1mo ago Changed · +23 lines · +7 tokens per session e8969fe84663
2mo ago First seen · 530 lines · 182 tokens per session scan A f8ce8613b977

Subscribe to this mod's changes

hex-review is a skill published in the GitHub repository grimoire-rs/grimoire (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 189 tokens to every session and 7,597 once invoked, about $0.0008 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 2026-09-08.

Code review Security agent-skills agents ai ai-agents anthropic claude

hex-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hex-reviewgrimoire-rs/grimoire	Skill	15	yesterday	Apache-2.0	A	189	Claude Code
oraclesteipete/oracle	Skill	4.1k	yesterday	MIT	A	18	Claude Code, Codex
pr-reviewaeonfun/aeon	Skill	788	yesterday	MIT	A	47	Claude Code, Codex
pr-triageaeonfun/aeon	Skill	788	yesterday	MIT	A	26	Claude Code, Codex
feedback-builderaeonfun/aeon	Skill	788	yesterday	MIT	A	45	Claude Code, Codex
[REPLACE: SKILL_NAME]aeonfun/aeon	Skill	788	yesterday	MIT	A	0	Claude Code, Codex
no-mistakesstevesolun/ctx	Skill	589	23d ago	MIT	A	67	Claude Code