using-plan

using-plan is a skill for Claude Code, Codex from JanYork/llm-wiki-cli. It costs 32 tokens per session (697 once invoked), scanned A, original, Apache-2.0.

A workflow for creating and maintaining a durable execution plan for a coding agent. It can track planned steps as work progresses, changes, pauses, completion, or abandonment.

In plain words
What is it for?
Use it to start, resume, advance, revise, block, complete, or abandon an agent work plan. It is intended for the LWC planning system.
Why use it?
It keeps a longer task’s current state and next steps available between actions. It also records when work is blocked or when the plan changes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the claude-lwc plugin — 8 skills, 7 hooks, 1 MCP server shipped together

Good fit Use it to start, resume, advance, revise, block, complete, or abandon an agent work plan. It is intended for the LWC planning system.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/janyork/llm-wiki-cli/using-plan
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.

Any agent
npx skills add JanYork/llm-wiki-cli --skill using-plan
Clone the repo
git clone --depth 1 https://github.com/JanYork/llm-wiki-cli

Made for: Claude Code, Codex.

Or install claude-lwc, the plugin that ships this one along with the rest of its 8 skills, 7 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for using-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-plan/github.svg)](https://agentmods.dev/skills/janyork/llm-wiki-cli/using-plan)
Your own site
<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-plan"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for using-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/janyork/llm-wiki-cli/using-plan"><img src="https://agentmods.dev/badge/skills/janyork/llm-wiki-cli/using-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00697
Opus 5.5 $0.00013 $0.00279
Sonnet 5.5 $0.00006 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured 1mo ago against content hash 5af522e4d0c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-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 1mo 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.

integrations/claude-lwc/skills/using-plan/SKILL.md · 29 lines

What it actually says

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

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 1mo ago Changed · +5 lines 5af522e4d0c2
  2. 2mo ago Changed · +2 lines 104e41855899
  3. 2mo ago First seen · 22 lines · 32 tokens per session scan A 536e9d763645

Subscribe to this mod's changes

using-plan is a skill published in the GitHub repository JanYork/llm-wiki-cli (72 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 697 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

using-plan compared with skills from other repositories

using-plan next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
using-planJanYork/llm-wiki-cliSkill721mo agoApache-2.0A32Claude Code, Codex
openspec-verify-changeFission-AI/OpenSpecSkill74kyesterdayMITA51Claude Code
openspec-new-changeFission-AI/OpenSpecSkill74kyesterdayMITA58Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k29d agoApache-2.0A138Claude Code, Codex
memory-systembojieli/ai-agent-bookSkill57k29d agoApache-2.0A95Claude Code, Codex
writingbojieli/ai-agent-bookSkill57k29d agoApache-2.0A27Claude Code, Codex
gsd-audit-milestoneopen-gsd/gsd-coreSkill11kyesterdayMITA17Claude Code