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/martian56/claude-engineer/plan-projectnpx skills add martian56/claude-engineer --skill plan-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/plan-project)<a href="https://agentmods.dev/skills/martian56/claude-engineer/plan-project"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/plan-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 | $0.00044 | $0.00606 |
| Opus 5 | $0.00022 | $0.00303 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
plan-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 5d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Project
Announce at start: "I'm using claude-engineer:plan-project to produce the phased plan."
Iron Law
NO BUILD WORK BEFORE THE USER SIGNS OFF ON THE PLAN. Violating the letter is violating the spirit.
Procedure (create a task per step)
- Decompose with
superpowers:writing-plans- turn the agreed brief into bite-sized, testable tasks; map the file structure first; right-size tasks; bake in DRY/YAGNI/TDD. - Impose the customer-experience-first phase order. Default phases:
- Phase 0 - Conventions & scaffold (
project-conventions,monorepo-and-tooling,docker-dev-environment). - Phase 1 - Design system (
design-system: DESIGN.md is the source of truth). - Phase 2 - Frontend shells & components (
frontend-development, on-token, WCAG AA). - Phase 3 - Backend APIs & data (
backend-development). - Phase 4 - Integration & end-to-end flows.
- Phase 5 - Quality, CI/CD, finish (
testing-and-quality,ci-cd-pipeline).
- Phase 0 - Conventions & scaffold (
- Write the plan as multiple files under
docs/plan/-00-overview.mdplus one file per phase (01-design-system.md,02-frontend.md, …), each with goals, tasks, file targets, and the per-phase "definition of done" (the four quality gates). - Record a decision log at
docs/plan/decisions.md(every non-obvious choice + why). - Initialize durable state via
claude-engineer:project-memory(creates.claude-engineer/memory.md,progress.md,current-phase.txt). - HARD SIGN-OFF GATE. Present the plan and explicitly ask the user to approve. Do not proceed to
claude-engineer:execute-builduntil they do.
Quality bar baked into every phase's "done"
Tests + coverage · Playwright E2E with zero console errors · WCAG AA · strict types + lint clean.
(See claude-engineer:testing-and-quality.)
Red flags - STOP
- About to scaffold/build code while still "planning" → stop; finish the plan and get sign-off.
- A phase has no concrete "definition of done" → add the four gates.
- The plan lives in one giant file → split into
docs/plan/*so it survives and stays scannable.
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.
- 5d ago First seen · 35 lines · 44 tokens per session scan A 7c79313a9e83
plan-project is a skill published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 606 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.
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.
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.
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.
dream
Memory consolidation - review, merge, prune, and index memory files. Run periodically to keep memories organized and up-to-date.