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/joaonic/agentkit/new-plannpx skills add Joaonic/agentkit --skill new-plangit clone --depth 1 https://github.com/Joaonic/agentkitWhat 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 | $0.00024 | $0.00737 |
| Opus 5 | $0.00012 | $0.00368 |
| Sonnet 5 | $0.00005 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
new-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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Plan
Purpose
Turn a request into a plan that can be executed without hidden assumptions.
Required Inputs
- user request or issue link
- affected modules and stack context
- architecture and policy constraints
- delivery constraints (deadline/dependency)
Fetch completo de issue (quando input é issue link)
Quando o input inclui uma issue do tracker, o agente deve consumir todos os campos antes de planear:
GitLab (default):
# 1. Body completo + metadata (labels, milestone, assignees, state, dates, web_url)
glab issue view <N> --output json
# 2. Todos os comentários/notas (decisões, feedback, mudanças de scope)
glab issue view <N> --comments
# 3. MRs já vinculados à issue (trabalho existente, branches abertas)
glab api "projects/:id/issues/<N>/related_merge_requests" 2>/dev/null || true
# 4. Issues relacionadas (parent, blocker, linked — dependências e fronteiras)
glab api "projects/:id/issues/<N>/links" 2>/dev/null || true
Exceção web/your-github-project (GitHub):
gh issue view <N> --json number,title,body,state,labels,milestone,assignees,url,comments
gh api "repos/{owner}/{repo}/issues/<N>/timeline" --jq '.[] | select(.event=="cross-referenced")' 2>/dev/null || true
Campos obrigatórios a usar no plano:
| Campo | Uso no plano |
|---|---|
description (body) |
Requisitos, scope, AC — base do work breakdown |
notes / comments |
Decisões posteriores, mudanças de scope, contexto técnico |
labels |
Prioridade, tipo de trabalho, área/módulo, flags (Blocked, needs-research) |
milestone |
Ciclo de entrega — informar deadline/constraints |
assignees |
Responsável — contacto para dúvidas |
related MRs |
Trabalho já feito — ajustar plano ao estado real |
linked issues |
Dependências, bloqueadores, parent — mapear para Dependencies section |
Não planear com base apenas no título ou resumo verbal do utilizador quando existe issue no tracker.
Mandatory Plan Structure
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 · 95 lines · 24 tokens per session scan A 98379912ef8b
new-plan is a skill published in the GitHub repository Joaonic/agentkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 737 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 2026-08-31.
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…