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/motlin/claude-code-plugins/import-plangit clone --depth 1 https://github.com/motlin/claude-code-pluginsWhat 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 | $0.00011 | $0.00853 |
| Opus 5 | $0.00005 | $0.00426 |
| Sonnet 5 | $0.00002 | $0.00171 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
import-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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import Plan
Convert a structured plan file from Claude Code's plan mode into individual tasks using TaskCreate, where each task references a specific step in the archived plan.
Locate the Plan File
- If
$ARGUMENTSis provided, use it as the plan file path. - Otherwise, use the plan file you remember writing or editing earlier in this conversation.
- If no plan was written in this conversation, pick the most recently modified
.mdfile in~/.claude/plans/, then confirm with the user viaAskUserQuestionthat it's the right plan — concurrent Claude sessions may be writing other plans into the same directory. - If
~/.claude/plans/has no.mdfiles, tell the user and stop.
Read the plan file to understand its structure and steps.
Archive the Plan Locally
- Create the
.llm/plans/directory if it does not exist - Choose a concise, descriptive name based on the plan content (e.g.,
add-import-plan-command) - Move the file:
~/.claude/plans/<original-name>.md→.llm/plans/<yyyy-mm-dd>-<descriptive-name>.md - Record the absolute path to the archived file for use in tasks
Create Tasks
For each step in the plan, create a task using TaskCreate with:
subject: A brief imperative description of the step (e.g., "Add validation to user input handler")activeForm: Present continuous form for spinner text (e.g., "Adding validation to user input handler")description: Full standalone context including all fields below
Each task's description must include:
- A brief description of what the step accomplishes
- An instruction line:
Read and follow step N from the plan at \`` - Key file paths and identifiers mentioned in that step (for standalone context)
Standalone Context
Each task is executed in isolation by an agent that can only see one task at a time via TaskGet. Therefore:
- Every task must contain ALL context needed to implement it
- Repeat shared context in every related task — if 5 tasks share the same background, repeat it 5 times
- Never reference other tasks — phrases like "similar to task above" are useless
- Include the full picture — source of inspiration, files involved, patterns to follow
- Use full absolute paths, exact class/function names, and specific implementation details
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 · 76 lines · 11 tokens per session scan A 345ae7b38597
import-plan is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 11 tokens to every session and 853 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.