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.
npx agentmods add commands/backnotprop/plannotator/plan-reviewgit clone --depth 1 https://github.com/backnotprop/plannotatorWhat 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 | $0.00018 | $0.01091 |
| Opus 5 | $0.00009 | $0.00545 |
| Sonnet 5 | $0.00004 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
plan-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 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan review is the core Plannotator workflow. It's not a slash command. Plannotator opens automatically when the host agent reaches its plan handoff point.
How it works
Claude calls ExitPlanMode
↓
PermissionRequest hook fires (hooks.json matcher: "ExitPlanMode")
↓
Bun server reads plan from stdin JSON (tool_input.plan)
↓
Server starts on random port, opens browser
↓
User reviews plan, optionally adds annotations
↓
Approve → agent proceeds with implementation
Deny → annotations sent as structured feedback
↓
Agent resubmits → Plan Diff shows what changed
The hook configuration lives at apps/hook/hooks/hooks.json and matches the ExitPlanMode tool name.
Codex flow
Codex does not expose a dedicated ExitPlanMode interception point. Instead, Plannotator integrates through Codex's experimental Stop hook.
Codex turn stops
↓
Stop hook fires
↓
Plannotator reads transcript_path rollout
↓
Latest completed plan item is extracted
fallback: raw <proposed_plan> block from assistant response
↓
Browser opens with the normal review UI
↓
Approve → turn stays completed
Deny → Stop hook returns continuation feedback
↓
Codex revises the plan in the same turn
↓
Plannotator reopens only if the revised plan actually changed
This means Codex plan review is post-render rather than pre-submit, but you still get the same annotations, plan history, diff view, and revision loop.
The macOS, Linux, and WSL installer enables this hook automatically when Codex is installed or ~/.codex already exists. Restart Codex Desktop or CLI after installing so the hook configuration is loaded.
Annotation types
When you select text in the plan, the annotation toolbar appears with these options:
| Type | What it does | Example |
|---|---|---|
| Deletion | Marks text for removal | "Remove this section" |
| Comment | Adds feedback on a section | "This needs error handling" |
| Quick label | Applies a preset label (⚡) | "Clarify this", "Needs tests", "Out of scope" |
| Looks good | Marks a section as approved (👍) | — |
| Global comment | General feedback (not tied to text) | "The plan looks good overall but needs tests" |
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 · 123 lines · 18 tokens per session scan A 2a1790791f1f
plan-review is a command published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,091 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.
Other commands, from other repositories
notebooklm
Vault-first source-grounded research via Gemini File Search. One command, no browser. The grounded parallel to /research-deep (which is open-web via Perplexity).
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
wikiweb
Command "wikiweb" from kimsanguine/llm-brain, covering 실행, 제공 기능 and 데이터가 없다면 (선택).
seo-compare
Compares the SEO of two pages or your page against a competitor. Shows differences in meta tags, structure, content, schema and speed side by side. TRIGGER when the user enters /seo-compare or asks to compare pages, analyze a competitor or see SEO differences between two URLs.
seo-crawl
Simulates how a crawler sees the site — reviews robots.txt, noindex directives, duplicate canonicals, redirect chains and accidentally blocked pages. TRIGGER when the user enters /seo-crawl or asks to review crawlability, indexing or how Google sees the site.
seo-structure
Reviews the site architecture — URL hierarchy, internal linking, click depth, orphan pages and internal authority distribution. TRIGGER when the user enters /seo-structure or asks to analyze the architecture, structure or internal linking of the site.