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.
git clone --depth 1 https://github.com/dean0x/devflowWrote 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.
[](https://agentmods.dev/commands/dean0x/devflow/code-review-levels)<a href="https://agentmods.dev/commands/dean0x/devflow/code-review-levels"><img src="https://agentmods.dev/badge/commands/dean0x/devflow/code-review-levels/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.
<a href="https://agentmods.dev/commands/dean0x/devflow/code-review-levels"><img src="https://agentmods.dev/badge/commands/dean0x/devflow/code-review-levels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00346 |
| Opus 5.5 | $0.00000 | $0.00138 |
| Sonnet 5.5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
code-review-levels 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 yesterday.
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.
What it actually says
Code review: focus sets by gate level
Sets
Each cell narrows one class's full set. keep: leaves only the named focuses; drop: removes them. A cell never adds a focus.
| Class | standard | lean |
|---|---|---|
code |
drop: typescript, dependencies (dependencies stays when a listed manifest changed) | keep: security, testing, reliability, compliance |
docs-only |
keep: documentation, consistency, security | keep: documentation, consistency, security |
tests-only |
keep: testing, reliability, consistency, security | keep: testing, reliability, security |
lockfile-only |
keep: dependencies, security | keep: dependencies, security |
Rules
- Manifests:
package.json,go.mod,go.work,Cargo.toml,pyproject.toml,requirements*.txt,CMakeLists.txt,Gemfile,composer.json,pom.xml,build.gradle*,setup.py,setup.cfg,Pipfile,*.csproj,Directory.*.props,Package.swift,Podfile,pubspec.yaml,build.sbt,mix.exs,deno.json. A path matches by file name. A lockfile alone is not a manifest change. - Mixed diff: apply each class's row to that class's own set, then take the union of the results, with no further cap.
- Security: every cell keeps
security. - Compliance: only the command's own trigger adds
compliance, on thecodeclass.
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.
- yesterday First seen · 20 lines · 0 tokens per session scan A 06f1bb9e587e
code-review-levels is a command published in the GitHub repository dean0x/devflow (20 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 346 tokens. 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 2026-10-16.
Other commands, from other repositories
greptile-review
Execute the full Greptile review cycle on a PR, looping until score meets threshold or circuit breaker triggers.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
code-review-give
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.
mach12:issue-review
Read a GitHub issue and all comments, review the implementation plan, and present findings.
review-design-verify
Phases 4-5 of reviewing-design-docs: Interface Verification + Implementation Simulation.