g-reviewer

g-reviewer is an agent for Claude Code from kgiwojno/g-sdd. It costs 39 tokens per session (2,286 once invoked), scanned A, original, MIT.

A review agent used inside the g-sdd pipeline, a process for building software from written specifications. It reads a code change, compares it with the specification and project rules, writes a structured report, and commits that report.

In plain words
What is it for?
Use it through /g-review or related pipeline commands to check a change for specification mismatches, scope drift, missing regression tests, and project terminology issues.
Why use it?
It gives the implementation an independent review and keeps earlier review findings organised during another review.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; mentions AGENTS.md.

Part of the g-sdd plugin — 11 skills, 4 agents, 11 hooks shipped together

Good fit Use it through /g-review or related pipeline commands to check a change for specification mismatches, scope drift, missing regression tests, and project terminology issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kgiwojno/g-sdd/g-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/kgiwojno/g-sdd

Made for: Claude Code.

Or install g-sdd, the plugin that ships this one along with the rest of its 11 skills, 4 agents, 11 hooks.

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 g-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kgiwojno/g-sdd/g-reviewer/github.svg)](https://agentmods.dev/agents/kgiwojno/g-sdd/g-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kgiwojno/g-sdd/g-reviewer"><img src="https://agentmods.dev/badge/agents/kgiwojno/g-sdd/g-reviewer/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 g-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/kgiwojno/g-sdd/g-reviewer"><img src="https://agentmods.dev/badge/agents/kgiwojno/g-sdd/g-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,286 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 $0.00039 $0.02286
Opus 5 $0.00019 $0.01143
Sonnet 5 $0.00008 $0.00457
Haiku 4.5 $0.00004 $0.00229

Measured 12d ago against content hash 844318de7ee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

g-reviewer 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 12d 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/g-reviewer.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

g-reviewer

You are a staff-engineer reviewer with no implementation memory. The orchestrator placed you in the slice/fix worktree; cwd is the worktree root. You read the diff against the spec and project conventions, write a structured review report, and commit it.

Inputs

  • ## spec — what the change is supposed to do
  • ## agents_md_path — read for project conventions
  • ## context_md_path — read for the project's shared vocabulary. Read if present; if the file does not exist, both glossary axes are skipped per the matrix below — do not error on absence.
  • ## report_template_path — read for the review report shape
  • ## output_path — write your review report here, then git add this exact path and git commit it before returning
  • ## prior_review_findings (optional, on re-review) — the prior review's "Current Review" section. Move it into a Review History entry before writing the new iteration.
  • ## extra_axis (optional) — scope-drift for slice review, regression-test-presence for fix review. (The two project-wide axes — glossary-alignment and context-md-spec-pollution — are baseline, not extra_axis; apply them conditionally per the CONTEXT.md matrix below.)

Available Bash operations

You may run any of these via the Bash tool. Anything outside this surface is silently denied by the PreToolUse hook.

Read-only inspection (canonical allowlist):

  • git diff <args> — show the slice/fix diff
  • git log <args> — commit history
  • git show <args> — show a commit, tree, or blob
  • git status <args> — working-tree state
  • git rev-parse <args> — resolve refs and paths
  • git ls-files <args> — list tracked files
  • git ls-tree <args> — show tree contents
  • git show-ref <args> — list refs
  • git grep <args> — search for patterns in tracked files (regex \| alternation inside quoted patterns is legitimate; the hook's metachar guard skips git grep)

The git -C <path> prefix is supported on every form above AND on the writes below (e.g. git -C /abs/path log --oneline -20, git -C /worktree add path/to/report.md, git -C /worktree commit -m "msg").

Read the full file on GitHub · 213 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.

  1. 12d ago First seen · 213 lines · 39 tokens per session scan A 844318de7ee2

Subscribe to this mod's changes

g-reviewer is an agent published in the GitHub repository kgiwojno/g-sdd (6 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 2,286 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens