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 skills add martian56/claude-engineer --skill intake-projectgit clone --depth 1 https://github.com/martian56/claude-engineerWrote 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.
[](https://agentmods.dev/skills/martian56/claude-engineer/intake-project)<a href="https://agentmods.dev/skills/martian56/claude-engineer/intake-project"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/intake-project.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00057 | $0.00569 |
| Opus 5 | $0.00028 | $0.00284 |
| Sonnet 5 | $0.00011 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
intake-project 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 7d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intake Project
Announce at start: "I'm using claude-engineer:intake-project to pin down what we're building."
Goal: a refined, mutually-agreed brief that the planning stage can turn into a phased plan.
Procedure (create a task per step)
- Find the brief. Look for
_private/initial-plan-draft.md.- Present → read it, then grill the user to fill gaps (see checklist below). Don't accept vagueness.
- Absent → run an interactive intake interview, then WRITE their answers into
_private/initial-plan-draft.md.
- Run the requirements/design dialogue via
superpowers:brainstorming. Do not skip - it is the discovery engine and the hard gate against premature building. - Resolve the stack decisions that the plan needs (defaults are opinionated; confirm only the genuinely open ones):
- Frontend: React (Vite SPA) vs Next.js - choose per the project type (see
claude-engineer:frontend-development). - JS package manager: Bun vs pnpm.
- Anything project-specific (auth model, external integrations, data shapes).
- Frontend: React (Vite SPA) vs Next.js - choose per the project type (see
- Capture the brief to
_private/initial-plan-draft.md: problem & users, core features (MoSCoW), the agreed stack choices, non-goals, constraints, any reference products/designs, success criteria. - Hand off to
claude-engineer:plan-project.
Intake checklist - the brief is not done until these are answered
- Who are the users and what is the one job-to-be-done?
- The 3 - 7 core features for v1, and explicit non-goals.
- React vs Next.js (and why); any second frontend?
- Design direction / brand / reference products (feeds the DESIGN.md in
claude-engineer:design-system). - Data model sketch and the key entities.
- Auth & roles? External services/APIs? Background jobs?
- Definition of success for v1.
Red flags - STOP and keep grilling
- "Let's just start coding." → No. Build is plan-gated.
- Features described as adjectives ("modern", "fast") with no concrete behavior.
- Stack chosen by habit without matching the project type.
- The user and you picture different products. Reflect the brief back until it matches.
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.
- 7d ago First seen · 38 lines · 57 tokens per session scan A b0098192179b
intake-project is a skill published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 569 once invoked, about $0.0003 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
adopt-project
Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or wants starter patterns…
commit-push-pr
Full git workflow - creates branch, commits, pushes, and creates or updates a PR with summary and test plan.
commit
Create a single well-crafted git commit from current changes. Analyzes diff, follows repo's commit style, and writes a concise "why not what" message.
remember
Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
dream
Memory consolidation - review, merge, prune, and index memory files. Run periodically to keep memories organized and up-to-date.