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 skills/franzos/claude-plugins/plan-newnpx skills add franzos/claude-plugins --skill plan-newgit clone --depth 1 https://github.com/franzos/claude-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 | $0.00072 | $0.00927 |
| Opus 5 | $0.00036 | $0.00464 |
| Sonnet 5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
plan:new 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning a change
$KBis your knowledge-base root: a directory outside the working repo holding<project>/specs/,<project>/plans/and<project>/checkpoints/. Point at it from your CLAUDE.md. Keeping these out of the repo keeps process artifacts from leaking into it, and the knowledge survives clones, branches and machines.
Produces two files in the knowledge base and nothing else. No implementation code is written in this skill.
Stop and say so if the change is small or mechanical (a bug fix, a one-file tweak, a rename). Those do not need a plan.
0. Locate the project
Project name is the repo's folder name, lowercase kebab-case. Everything lands under $KB/<project>/.
Pick a slug now (kebab-case, describes the change, no date). The spec, the plan, and every checkpoint share it.
1. Q&A before anything else
Ask the user about what is underspecified. Use AskUserQuestion for real forks; plain prose for open questions. Batch related questions rather than drip-feeding them.
Ask about: the actual problem being solved, scope boundaries (what is explicitly not in this change), constraints, what "done" looks like, and anything the codebase cannot tell you.
Do not assume and do not proceed on a guess. If two readings of the request lead to materially different work, that is a question, not a judgment call.
2. Understand what exists
For a brownfield change, dispatch feature-dev:code-explorer with a specific question - the feature to trace, the subsystem to map. Ask it to return the files that matter most, then read those directly.
Do not explore the codebase inline. That is what the agent is for.
Skip this for greenfield work.
3. Write the spec
$KB/<project>/specs/YYYY-MM-DD-<slug>.md
The spec is the what and why, authoritative over everything downstream. It carries: the problem, the decisions taken and their rationale, explicit non-goals, constraints, and open questions still outstanding. Prose over bullets where the reasoning matters.
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 · 78 lines · 72 tokens per session scan A 59f6de1b9e15
plan:new is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 21d ago), licensed MIT. It adds 72 tokens to every session and 927 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…