Claude Skill

using-plan

Use when an Agent needs to create, resume, advance, block, revise, complete, or abandon a durable current execution plan in LWC.

LLM Mart · 0 points · 9 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download JanYork-llm-wiki-cli-integrations_pi-lwc_skills_using-plan-11e869f.zip · 1 KB

janyork/llm-wiki-cli 56 6 forks Apache-2.0 Updated 12d ago

Part of janyork/llm-wiki-cli — 28 skills

Install

skills CLI npx skills add https://github.com/JanYork/llm-wiki-cli/tree/main/integrations/pi-lwc/skills/using-plan

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install janyork-llm-wiki-cli@llmmart

Git git clone https://github.com/JanYork/llm-wiki-cli.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole janyork/llm-wiki-cli collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Using LWC Plan

Reuse current readiness/config facts; run lwc config show only when the setting is unknown or stale. Continue only when plan.setting is enabled. A Skill trigger is not consent to enable Plan: when disabled, do not run Plan commands; explain that the user can opt in with lwc config set --plan enabled. A lifecycle Hook with a resolved agent_context includes only Plans explicitly tracked by that Agent context. Treat any Plan progress reminder for another context as unrelated and ignore it.

Use Plan only for the current coarse execution plan. It is independent from Todo and must never be converted to or from a Todo automatically.

Create one objective, explicit done criteria, constraints, and ordered coarse steps.
After creating or explicitly claiming a Plan, bind it with lwc --scope project|global plan track PLAN_ID --context CONTEXT_ID, using only the opaque ID from the current Hook's LWC_READINESS.agent_context. Never infer or copy another Agent's context.
Resume with lwc plan brief PLAN_ID; it is bounded and contains no hidden reasoning.
Treat Hook plan.tracking and plan.additional_trackings as continuity cues for this context only. Follow the current step and planned next step, but call brief before any mutation.
Use exact, idempotent plan untrack PLAN_ID --context CONTEXT_ID before deliberately switching a context to another Plan; a conflicting track never replaces the current association.
Before mutation, inspect the current revision and pass --if-revision.
advance completes the focal step with a result and explicitly selects the next pending step.
block records a concrete blocker. revise requires a reason and CAS revision. Inspect lwc contract plan-revise for its full schema and example.
Prefer a targeted revision of objective, done_when, constraints, or updates by stable step ID. Use current_step when changing focus. The replacement steps form supersedes unfinished work and cannot be mixed with ID updates.
Use disposition: waived with an explicit user-instruction basis for waived work; use superseded for replaced work. Neither means verification passed. Terminal steps cannot be rewritten.
Mutation receipts show changed steps; lwc plan show PLAN_ID and --full expose full records. lwc plan history PLAN_ID returns revision evidence.
lwc plan reconcile PLAN_ID --from plan.md is read-only: it returns title-matched event candidates and a textual document comparison. It does not infer semantic agreement or advance the plan. Review evidence before a CAS mutation.
Keep execution state in this Plan. File maps should point to it, not mirror its progress. Use Wiki for stable knowledge and Memory for historical evidence.
Complete only after all steps are terminal, evidence is supplied, and done criteria were checked.
Use project/global for exact reads and writes. Use --scope all only for current/list/search.
On a revision or request conflict, reload and reconcile; never overwrite blindly.
Do not use --changeset with Plan commands.

Files (llm-wiki-cli)

agents

openai.yaml 195 B

interface:
  display_name: "LWC Plan"
  short_description: "Durable current execution plan"
  default_prompt: "Use $using-plan to resume and update the current plan through explicit milestones."

SKILL.md 3.2 KB

---
name: using-plan
description: Use when an Agent needs to create, resume, advance, block, revise, complete, or abandon a durable current execution plan in LWC.
---

# Using LWC Plan

Reuse current readiness/config facts; run `lwc config show` only when the setting is unknown or stale. Continue only when `plan.setting` is `enabled`. A Skill trigger is not consent to enable Plan: when disabled, do not run Plan commands; explain that the user can opt in with `lwc config set --plan enabled`. A lifecycle Hook with a resolved `agent_context` includes only Plans explicitly tracked by that Agent context. Treat any Plan progress reminder for another context as unrelated and ignore it.

Use Plan only for the current coarse execution plan. It is independent from Todo and must never be converted to or from a Todo automatically.

- Create one objective, explicit done criteria, constraints, and ordered coarse steps.
- After creating or explicitly claiming a Plan, bind it with `lwc --scope project|global plan track PLAN_ID --context CONTEXT_ID`, using only the opaque ID from the current Hook's `LWC_READINESS.agent_context`. Never infer or copy another Agent's context.
- Resume with `lwc plan brief PLAN_ID`; it is bounded and contains no hidden reasoning.
- Treat Hook `plan.tracking` and `plan.additional_trackings` as continuity cues for this context only. Follow the current step and planned next step, but call `brief` before any mutation.
- Use exact, idempotent `plan untrack PLAN_ID --context CONTEXT_ID` before deliberately switching a context to another Plan; a conflicting `track` never replaces the current association.
- Before mutation, inspect the current revision and pass `--if-revision`.
- `advance` completes the focal step with a result and explicitly selects the next pending step.
- `block` records a concrete blocker. `revise` requires a reason and CAS revision. Inspect `lwc contract plan-revise` for its full schema and example.
- Prefer a targeted revision of `objective`, `done_when`, `constraints`, or `updates` by stable step ID. Use `current_step` when changing focus. The replacement `steps` form supersedes unfinished work and cannot be mixed with ID updates.
- Use `disposition: waived` with an explicit user-instruction `basis` for waived work; use `superseded` for replaced work. Neither means verification passed. Terminal steps cannot be rewritten.
- Mutation receipts show changed steps; `lwc plan show PLAN_ID` and `--full` expose full records. `lwc plan history PLAN_ID` returns revision evidence.
- `lwc plan reconcile PLAN_ID --from plan.md` is read-only: it returns title-matched event candidates and a textual document comparison. It does not infer semantic agreement or advance the plan. Review evidence before a CAS mutation.
- Keep execution state in this Plan. File maps should point to it, not mirror its progress. Use Wiki for stable knowledge and Memory for historical evidence.
- Complete only after all steps are terminal, evidence is supplied, and done criteria were checked.
- Use project/global for exact reads and writes. Use `--scope all` only for current/list/search.
- On a revision or request conflict, reload and reconcile; never overwrite blindly.
- Do not use `--changeset` with Plan commands.