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 skills add zjp1997720/zhijian-skills --skill light-plan-and-workgit clone --depth 1 https://github.com/zjp1997720/zhijian-skillsWrote 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.
[](https://agentmods.dev/skills/zjp1997720/zhijian-skills/light-plan-and-work)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/light-plan-and-work"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/light-plan-and-work/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.
<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/light-plan-and-work"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/light-plan-and-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00062 | $0.00695 |
| Opus 5 | $0.00031 | $0.00347 |
| Sonnet 5 | $0.00012 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
light-plan-and-work 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 12d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Light Plan and Work
Planning and doing are one continuous workflow.
Route before planning
Read the request, relevant project instructions, current files, and repository state. Choose one route:
- Direct execution: one or two obvious actions. State a one-line brief and do them; do not manufacture a plan.
- Light plan and work: the outcome is concrete, the scope is bounded, and 3–7 steps can complete and verify it.
- Specialist Skill: a narrower installed Skill owns the artifact or domain. Use it, with this Skill only as the execution wrapper when useful.
- Discovery or brainstorming: the user is still choosing the problem, audience, concept, story, or direction. Use a discovery Skill before planning.
- Heavy workflow: use the project's full specification or plan/work system when consequence, ambiguity, or coordination cost is high.
Heavy conditions include destructive or sensitive operations, migrations, public API changes, cross-system architecture, releases, multiple owners, unresolved acceptance criteria, and explicit requests for a full specification or Compound Engineering. Read routing and verification when the route is unclear.
Execute
- Lock a compact execution brief: Goal, Deliverable, Boundary, and Acceptance.
- Resolve reversible choices yourself. Ask one blocking question only when the answer changes the outcome or requires new authority.
- Use the host plan tracker for 3–7 observable steps, with at most one step in progress. Each step must produce or verify something.
- Start after the plan is visible. Read before editing, preserve unrelated work, follow project instructions, and keep the plan aligned with evidence.
- If a heavy condition appears, preserve completed safe work, pause the affected mutation, explain the evidence, and switch to the heavier workflow.
- Verify in proportion to risk. Distinguish checks that directly cover the task from repository-wide or environment-wide gates.
- When a broad gate fails, classify the failure before acting. If read-only evidence shows it comes from pre-existing, unrelated work, preserve that work, run the strongest safe task-scoped checks, and record the blocked gate without claiming the repository is fully green. If the failure overlaps task files, causality is uncertain, or the gate is required for a release, treat it as a task blocker and fix, pause, or escalate.
- Hand back the result, artifacts, evidence, blocked gates, and residual risk.
What ships with it
8 files 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.
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.
- 12d ago First seen · 39 lines · 62 tokens per session scan A 600e036133e8
light-plan-and-work is a skill published in the GitHub repository zjp1997720/zhijian-skills (680 stars, last pushed 6d ago), licensed MIT. It adds 62 tokens to every session and 695 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…