A project setup command for the mindfunnel workflow. It creates the project’s standard agent-instruction and project-context files, including AGENTS.md, CLAUDE.md, and PROJECT.md.

Initializing a project once, creating compatibility links for Claude Code, adding an empty project context file, and removing legacy setup links.

It gives contributors and coding agents a consistent place to find project guidance and context, while cleaning up older setup files safely for repeated use.

prime — Skill by emaballarin

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.

agentmods

npx agentmods add skills/emaballarin/ccplugins/prime

Any agent

npx skills add emaballarin/ccplugins --skill prime

Clone the repo

git clone --depth 1 https://github.com/emaballarin/ccplugins

Made for: Claude Code, Codex.

Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,556 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00162	$0.03556
Opus 5	$0.00081	$0.01778
Sonnet 5	$0.00032	$0.00711
Haiku 4.5	$0.00016	$0.00356

Measured yesterday against content hash a873005ff3d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prime 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 yesterday.

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.

plugins/mindfunnel/skills/prime/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mf:prime — prime a project for the mindfunnel workflow

Set up the current project's root with a small committed agent-entry-point so that every contributor — with or without the mindfunnel plugin installed — sees a clean project-scoped AGENTS.md on clone:

AGENTS.md — project-scoped stub (copied from templates/project-AGENTS.md), real file, committed. Maintainers extend it per-project as the project grows.
CLAUDE.md — intra-repo symlink to ./AGENTS.md, committed. Explicit Claude Code compatibility.
PROJECT.md — real file, empty by default, committed. Holds project-specific deep context.

Nothing per-project points into ~/.mindfunnel/ anymore. The maintainer's user-global engineering style (~/.mindfunnel/AGENTS.md) is loaded independently via the ~/.claude/CLAUDE.md / ~/.codex/instructions.md symlinks that /mf:setup manages; it is not conflated with each project's AGENTS.md. Likewise, SOUL.md and USER.md are user-global files reached via ~/.claude/ and ~/.codex/ symlinks and are never stamped into a project.

Run once per project, from the project root. Idempotent: re-running after the upgrade cleans up legacy pre-0.3.0 symlinks and legacy .gitignore lines automatically.

Important

Run from the project root. The skill writes into the current working directory. Confirm with pwd before acting if there's any doubt.
Never overwrite a pre-existing regular file. A hand-authored ./AGENTS.md or ./CLAUDE.md always wins over the stub; leave it alone and flag in the report.
~/.mindfunnel/ must already be set up. If it isn't, stop and tell the user to run /mf:setup first. (The stub template lives inside the plugin, not in ~/.mindfunnel/, but /mf:setup is still the prerequisite for the rest of the workflow.)
.gitignore edits are minimal, targeted, and one-way. /mf:prime strips AGENTS.md and CLAUDE.md lines from .gitignore if they're there (required — leaving them would prevent the new committed files from staging). It does not touch the legacy SOUL.md line (harmless, orthogonal to this change).

Read the full file on GitHub · 241 lines

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.

yesterday First seen · 241 lines · 162 tokens per session scan A a873005ff3d2

Subscribe to this mod's changes

prime is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 162 tokens to every session and 3,556 once invoked, about $0.0008 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.

Productivity claude-code claude-code-plugin claude-skills

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens