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/ndom91/open-plan-annotator/annotate-plangit clone --depth 1 https://github.com/ndom91/open-plan-annotatorWhat 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 | $0.00014 | $0.00378 |
| Opus 5 | $0.00007 | $0.00189 |
| Sonnet 5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
annotate-plan 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
The user wants a plan drafted and reviewed via the open-plan-annotator UI before any implementation. This is required, not optional.
Task to plan: $ARGUMENTS
Steps:
- Enter plan mode (
EnterPlanMode). - Investigate the codebase as needed to draft a concrete plan. Include:
- Brief summary of what you understood the task to require
- Specific files you intend to create or modify and why
- Any assumptions you are making
- Tradeoffs and option comparisons inline (do NOT pull these into chat — they belong in the plan body where the user can comment on each one)
- Explicit questions if anything is ambiguous
- Call
ExitPlanModewith the plan. This triggers the open-plan-annotator browser UI. - The user will annotate the plan (deletions, replacements, insertions, comments) in the browser.
- If the user denies with annotations, revise the plan based on their feedback and re-exit plan mode.
- Only begin implementation after the user approves.
Hard rules:
- Do not skip plan mode.
- Do not paste a plan inline and ask "sound good?" — that bypasses the annotator UI the user installed this plugin for.
- Do not collapse into a 2-3 sentence inline response just because the user message contains an exploratory clause like "what do you think?" alongside directive items. Mixed signals still route through the annotator.
- Self-check the response before sending: if it contains a "Plan:" / "Steps:" / "Concrete changes:" header, 3+ file paths, or ends with "OK to proceed?" — discard and route through the annotator instead.
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 · 30 lines · 14 tokens per session scan A d8006d8037b7
annotate-plan is a command published in the GitHub repository ndom91/open-plan-annotator (90 stars, last pushed 14d ago), licensed MIT. It adds 14 tokens to every session and 378 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
fd-task
Define a task end to end — auto-init the workspace, research the codebase, confirm requirements, and save task.md + architecture.md + affect.md + plan.md.
fd-execute
Implement plan.md with the TDD pipeline — parallel worktree guard from affect.md, wave-based execution, checkpoint after each wave.
fd-done
Close the task — summarize built vs required, then commit and push on confirmation.
fd-review
Two-lens review of the task artifacts before execution — CEO review challenges scope and premise, eng review checks architecture, edge cases, and blast radius.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.
fd-resume
Restore from checkpoint.json (falling back to STATE.md) — brief the user, PAUSE for confirmation, then continue from the recorded command and stage.