Agent Skill
Plan skill
planjeremylongshore/tons-of-skills-marketplaceplugins/ai-agency/hyperflow/skills/plan/SKILL.md
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request doesn't need, then STOPS at a build-location gate (build here, hand off to another session, or just keep the plan). Plan never implements. Trigger with /hyperflow:plan, "design this", "plan this", "decompose this", "how should we", "what's the best way to", "break this down", "enhance this prompt".
always on
144 tokname + description
once used
9,197 tokSKILL.md body
bundled files
28 KB
repo stars
2.9kGitHub
Install the Plan skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill plan
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace mkdir -p ~/.claude/skills cp -R /tmp/tons-of-skills-marketplace/plugins/ai-agency/hyperflow/skills/plan ~/.claude/skills/plan
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 144 tok |
| When the agent uses it | The SKILL.md instructions | 9,197 tok |
| Only if opened | 2 bundled files (8 KB) | varies |
Until it is used, plan costs about 9.5× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 150 skills from jeremylongshore/tons-of-skills-marketplace would load 9,741 tokens of descriptions. Skills vs MCP study
Checks
- The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(git:*), Bash(python3:*), Bash(mv:*), Glob, Grep, Agent, AskUserQuestion, Skill. The agent can use these without asking while the skill is active.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Plan
- Iron Rules
- Per-Step Agent Map (DOCTRINE rule 12 + 12.2)
- Approval Gates
- Flow
- Step 0 — Setup (silent · max thinking · NO gate)
- Step 1 — Triage (Layer 0.5 · P3-concurrent with Step 3)
- Step 2 — Amplify / prompt hygiene (atomic · skippable)
- Step 3 — Context exploration (P1 sub-phases · P3-concurrent with Step 1)
- Step 4 — Multi-dimensional analysis (P4-skippable)
- Step 5 — Clarify (AskUserQuestion · two modes)
- Step 6 — Synthesis + approaches (P3 + P2 · P4-skippable)
- Step 7 — Section-by-section design (P1 + P2 · file-first · one combined gate)
- Step 8 — Spec finalize (atomic)
- Step 9 — Decompose (Planner · 9a sequential then 9b/9c parallel)
- Step 10 — Write task file (P3 sub-phases · concurrent with Step 11)
- Step 11 — Memory (P3 · concurrent with Step 10)
- Step 12 — Build-location gate (ALWAYS fires · plan never auto-implements)
- Anti-Patterns
- Overview
- Prerequisites
- Error Handling
- Resources
More skills from jeremylongshore/tons-of-skills-marketplace
- agency-osjeremylongshore/tons-of-skills-marketplace
Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or natural-language variants ("add a suggestion: …", "let's discuss X", "run the queue").
2.9k1142 tok idle · 1,602 in use - apexjeremylongshore/tons-of-skills-marketplace
Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
2.9k31 tok idle · 210 in use - apex-planjeremylongshore/tons-of-skills-marketplace
Plan and scope a project — discovery, challenge assumptions, present S/M/L options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.
2.9k56 tok idle · 663 in use - apex-reconjeremylongshore/tons-of-skills-marketplace
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
2.9k58 tok idle · 675 in use - apex-reviewjeremylongshore/tons-of-skills-marketplace
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
2.9k46 tok idle · 630 in use - apex-statusjeremylongshore/tons-of-skills-marketplace
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
2.9k41 tok idle · 258 in use - apex-takeoverjeremylongshore/tons-of-skills-marketplace
System takeover — take ownership of an existing codebase or inherited system. Use when "we acquired this", "previous team left", "take over this system", "inherited this codebase".
2.9k45 tok idle · 727 in use - atlasjeremylongshore/tons-of-skills-marketplace
Knowledge engineer — architecture docs, ADRs, diagrams, changelogs, onboarding, and reports.
2.9k22 tok idle · 219 in use