A command that turns a Claude Code plan or specification file into a task file, with an option to hand it to Cursor. Cursor is a coding agent that can work on delegated tasks.

Use it to convert plan files into tasks, preview the result, and optionally send the task to Cursor.

It removes the need to manually copy a plan into a task and prepare the handoff. You can review the generated task first or delegate it automatically.

from-plan — Command by freema

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 commands/freema/cursor-plugin-cc/from-plan

Clone the repo

git clone --depth 1 https://github.com/freema/cursor-plugin-cc

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 550 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.

Model	Per session	Once invoked
Fable 5	$0.00023	$0.00550
Opus 5	$0.00012	$0.00275
Sonnet 5	$0.00005	$0.00110
Haiku 4.5	$0.00002	$0.00055

Measured 2d ago against content hash 53a052a8de27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

from-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 2d 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.

plugins/cursor/commands/from-plan.md · 29 lines

What it actually says

!node "${CLAUDE_PLUGIN_ROOT}/scripts/from-plan.mjs" -- "$ARGUMENTS"

Render the output verbatim. The command has two modes:

Preview + hand back (default): it writes the task file, then prints the exact /cursor:delegate @… command. Run that command yourself after reviewing the task file.
Auto-delegate (--delegate or --yes): it writes the task file AND immediately calls /cursor:delegate, so the output merges into a single flow.

Without arguments it picks the newest plan under ~/.claude/plans/. Pass a name fragment (e.g. dark-mode) or any path (e.g. PRPs/dark-mode.md) to pick a specific one. --list shows the 15 most recent plan files.

Where the task file lands — derived from the spec, most- to least-specific:

--out-dir <dir> for a single run
the directory the source spec lives in — pass PRPs/018.md and the task file joins it there, in whichever repo that is
the CURSOR_PLUGIN_CC_TASKS_DIR environment variable
the per-repo default: /cursor:setup --tasks-dir PRPs (reset with --no-tasks-dir)
tasks/

Rule 2 means spec-driven projects need no configuration, and it keeps working when specs are centralised in one repo while code lives in siblings. Rules 3–5 only come into play for Claude's own plan-mode files, which have no project location to inherit. Relative values resolve against the repo root, so the destination does not move when you run the command from a subdirectory.

The spec may live outside the current repo. When it does, Cursor is handed an absolute path instead of @path (which cannot leave the repo root), and told to apply its changes in the current repository. Report that note to the user when it appears.

--in-place skips the conversion entirely and delegates the source document as written — no task file is created. Use it when your spec already is the task (PRP, Spec Kit, OpenSpec). Works across repos.

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.

2d ago First seen · 29 lines · 23 tokens per session scan A 53a052a8de27

Subscribe to this mod's changes

from-plan is a command published in the GitHub repository freema/cursor-plugin-cc (34 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 550 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.

Planning Project management agent-delegation ai-coding claude-code claude-code-plugin composer-2 cursor

from-plan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

tasks

constitution

taskstoissues

taskstoissues

change-manager

tasks