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/code-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 | $0.00023 | $0.04284 |
| Opus 5 | $0.00012 | $0.02142 |
| Sonnet 5 | $0.00005 | $0.00857 |
| Haiku 4.5 | $0.00002 | $0.00428 |
Grade A, and why
code-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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The /plannotator-review command opens an interactive code review UI for your local changes or a GitHub pull request.
Usage
Review local changes:
/plannotator-review
Review a GitHub pull request:
/plannotator-review https://github.com/owner/repo/pull/123
PR review uses the gh CLI for authentication, so private repos work automatically if you're authenticated with gh auth login.
GitLab merge request URLs are also supported when the glab CLI is installed and authenticated.
How it works
Local review:
User runs /plannotator-review
↓
Agent runs: plannotator review
↓
the detected VCS provider captures changes
↓
Review server starts, opens browser with diff viewer
↓
User annotates code, provides feedback
↓
Send Feedback → feedback sent to agent
Approve → configured approval prompt sent to agent
PR review:
User runs /plannotator-review <github-url>
↓
Agent runs: plannotator review <github-url>
↓
gh CLI fetches PR diff and metadata
↓
Review server starts, opens browser with diff viewer
↓
User annotates code, provides feedback
↓
Send Feedback → PR context included in feedback
Approve → configured approval prompt sent to agent
Stacked PRs and MRs
When a PR or MR targets a non-default branch, Plannotator marks it as stacked in the review header. The default view remains Layer, which matches the platform diff and is the safe mode for posting inline review comments.
If Plannotator has a local checkout for the PR or MR, the header also offers Full stack. Full stack shows everything from the repository default branch through the current checked-out head, which helps you understand the whole chain before reviewing the current layer.
Platform posting is intentionally limited to Layer because GitHub and GitLab inline comments are anchored to the PR or MR's own diff. Use Full stack for comprehension and agent review, then switch back to Layer before posting to the platform.
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 · 269 lines · 23 tokens per session scan A 2723b1701a52
code-review is a command published in the GitHub repository backnotprop/plannotator (8,256 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 4,284 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
kg-ingest
Ingest a source document into the Knowledge Graph - extract entities, concepts, create wiki pages.
kg-init
Initialize a new Knowledge Graph with raw/ and wiki/ structure.
kg-lint
Health check the Knowledge Graph - find orphans, contradictions, gaps, stale claims.
kg-project
Create a new project in the Knowledge Graph with ADR tracking.
kg-query
Query KG (supports: active, recent, search , decisions , plan ).
kg-setup
Configure Knowledge Graph path and create config file.