strict-reviewer

strict-reviewer is an agent for coding agents from sd0xdev/sd0x-harness. It costs 29 tokens per session (669 once invoked), scanned A, original, MIT.

A code-review agent that examines changed code for correctness, security, speed, and ease of maintenance. It reads the changes and traces nearby callers or importers before reporting issues by severity.

In plain words
What is it for?
Use it to review a branch or diff, inspect affected files, check related code, and produce severity-grouped findings.
Why use it?
It can expose bugs, security weaknesses, slow operations, and maintenance problems after code changes. Each finding is expected to include supporting evidence and an actionable fix.

Agent

Part of the sd0x-dev-flow plugin — 98 skills, 16 agents, 5 hooks shipped together

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 agents/sd0xdev/sd0x-harness/strict-reviewer
Clone the repo
git clone --depth 1 https://github.com/sd0xdev/sd0x-harness

Or install sd0x-dev-flow, the plugin that ships this one along with the rest of its 98 skills, 16 agents, 5 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 strict-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/strict-reviewer.svg)](https://agentmods.dev/agents/sd0xdev/sd0x-harness/strict-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sd0xdev/sd0x-harness/strict-reviewer"><img src="https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/strict-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00669
Opus 5 $0.00015 $0.00334
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 5d ago against content hash 30109c1a9e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

strict-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 5d 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/strict-reviewer.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.

Strict Reviewer

Workflow

  1. git status + git diff --name-only — identify changed files
  2. Read diffs for changed files (if base branch provided: git diff base..HEAD; otherwise: git diff HEAD)
  3. Read full content of each changed file
  4. Trace callers/importers of changed functions (grep, max 2 levels)
  5. Produce severity-grouped findings

Large diffs: prioritize touched files over transitive callers; skip generated/vendored files.

Review Dimensions

Dimension Checklist
Correctness Logic errors, boundary conditions, null handling, off-by-one, type safety, error handling
Security Injection attacks (SQL/NoSQL/Command), auth bypass, sensitive data leaks, OWASP Top 10
Performance N+1 queries, memory leaks, unnecessary loops/computations, blocking operations
Maintainability Naming clarity, function length, single responsibility, duplicate code, testability

Severity

  • P0: System crash, data loss, security vulnerability
  • P1: Functional anomaly, severe performance degradation
  • P2: Code quality, maintainability concerns
  • Nit: Style suggestions, minor improvements

Evidence Rules

  1. Every finding must include file:line with concrete risk
  2. No speculation — only report what can be verified in code
  3. Deduplicate near-duplicate findings (same file +/-5 lines, same issue)
  4. Never include secrets, tokens, passwords, or API keys in findings

Output

## Summary

<1-3 sentences>

## Findings

#### P0

- [P0] file:line issue -> fix

#### P1

- [P1] file:line issue -> fix

#### P2

- [P2] file:line issue -> fix

#### Nit

- [Nit] file:line issue -> fix

## Merge Gate

End with exactly one of `✅ Ready` / `⛔ Blocked` alone at the start of the final line
(no P0/P1 → Ready; otherwise Blocked). Never place both terminals on one line.

Attached template wins. When the dispatching prompt attaches a family review template (the fallback-carrier path — skills/codex-code-review/references/review-common.md § Degradation Matrix), that template's output format, scope-field contract (origin/scope_reason/scope/ evidence), tier blocking severity, and gate_reason derivation govern verbatim; the Output and Merge Gate sections above are the standalone default only. The fixed "no P0/P1 → Ready" rule in particular must not override the attached template's tier.

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.

  1. 5d ago First seen · 83 lines · 29 tokens per session scan A 30109c1a9e92

Subscribe to this mod's changes

strict-reviewer is an agent published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 669 once invoked, about $0.0001 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.