project-brief

project-brief is a skill for Claude Code from MarcoZorn/agencykit. It costs 38 tokens per session (2,359 once invoked), scanned A, original, MIT.

A project-planning guide that turns an informal client request into a structured brief with goals, phases, tasks, owners, deadlines and risks.

In plain words
What is it for?
Use it to prepare new client projects, define scope and organise work for tools such as Asana, ClickUp or Notion.
Why use it?
It fills in the missing structure between a vague request and work a team can start. It also highlights important questions before planning begins.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Codex; built for openclaw.

Good fit Use it to prepare new client projects, define scope and organise work for tools such as Asana, ClickUp or Notion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcozorn/agencykit/project-brief
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.

Any agent
npx skills add MarcoZorn/agencykit --skill project-brief
Clone the repo
git clone --depth 1 https://github.com/MarcoZorn/agencykit

Made for: Claude Code.

Wrote 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.

agentmods badge for project-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcozorn/agencykit/project-brief/github.svg)](https://agentmods.dev/skills/marcozorn/agencykit/project-brief)
Your own site
<a href="https://agentmods.dev/skills/marcozorn/agencykit/project-brief"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/project-brief/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.

agentmods 80×15 button for project-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcozorn/agencykit/project-brief"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/project-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.02359
Opus 5 $0.00019 $0.01179
Sonnet 5 $0.00008 $0.00472
Haiku 4.5 $0.00004 $0.00236

Measured 9d ago against content hash e2ac13a2e9c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

project-brief 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 9d 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.

.claude/skills/project-brief/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Brief

When to use this skill

English: "new project", "start a project", "client brief", "project kickoff", "set up a new client project", "scope this project".

Italiano: "nuovo progetto", "nuovo cliente", "brief progetto", "imposta progetto", "kickoff".

What this skill does

Takes a vague, half-formed client request and turns it into a complete project brief a whole team can execute from: a clear objective, the operational phases, a task list with owners and deadlines, and the risks worth naming before they become fires. The output is structured so it can be pasted straight into a project management tool without reformatting.

Inputs required

Before generating anything, ask these five questions and wait for the answers. Do not guess.

  1. Client name — who is this for?
  2. Service type — social media management, video production, web build, branding, campaign, retainer, other?
  3. Deadline — hard delivery date, or the first milestone if it is an ongoing retainer.
  4. Budget range — even a rough band. It sets the ambition and the team size.
  5. Main KPI — the one number that defines success (followers, leads, sales, views, delivery on time).

If the user cannot answer one, mark it TBD in the output and add a task to confirm it. Never invent a budget or a deadline.

Output format

Two blocks, in this order:

  1. RECAP PROGETTO — the header card: client, service, objective, deadline, owner, teams, status, priority.
  2. FASI OPERATIVE — a phase table.
  3. TASK — the task list.
  4. RISCHI E BLOCCHI — named risks with impact and mitigation.

Everything is plain Markdown tables and lists so it survives a copy-paste into Asana, ClickUp or Notion.


Brand voice

If a BRAND.md file exists in this skill's folder (.claude/skills/project-brief/BRAND.md) or in .claude/brand/BRAND.md (global fallback), read it before generating output and apply its tone, terminology, and examples to all text you produce. A skill-local BRAND.md overrides the global one; if neither exists, use a clean, professional default voice.

Read the full file on GitHub · 188 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.

  1. 9d ago First seen · 188 lines · 38 tokens per session scan A e2ac13a2e9c4

Subscribe to this mod's changes

project-brief is a skill published in the GitHub repository MarcoZorn/agencykit (6 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 2,359 once invoked, about $0.0002 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.