project-initializer

A project setup agent that turns a specification, issue, or feature request into a tracked list of deliverables and basic project files. It is intended for a repository-level feature workflow.

In plain words
What is it for?
Use it at the start of a project to create a feature list, setup script, verification configuration, project status, and an initial commit.
Why use it?
It removes the need to manually break a vague request into ordered, independently deliverable tasks and create the initial verification setup.

Skill for Claude CodeCodex

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/demondamon/agenticx/project-initializer
Any agent
npx skills add DemonDamon/AgenticX --skill project-initializer
Clone the repo
git clone --depth 1 https://github.com/DemonDamon/AgenticX

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00620
Opus 5 $0.00017 $0.00310
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00003 $0.00062

Measured 2d ago against content hash ebe84b87e1d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-initializer 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 2d 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.

agenticx/skills/bundled/project-initializer/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Initializer

Use exactly once per project, when session_mode == feature_loop and .agx/project/ does not yet exist (system prompt will say "Initializer 阶段").

Inputs

  • A spec markdown, GitHub issue, or natural-language feature description.
  • The repo root (workspace_dir or first non-default taskspace).

Steps

  1. Read the spec end-to-end. Use file_read if the user pointed at a file, otherwise capture the user's message as the source of truth.
  2. Decompose into ≥ 5 deliverables. Each feature must:
    • have a stable id (kebab-case, ≤ 32 chars),
    • be independently mergeable (its commit can land on main without breaking others),
    • declare 1–3 concrete acceptance_criteria (observable behavior, not implementation steps),
    • declare depends_on only for hard ordering constraints,
    • get an integer priority (lower = sooner; reserve 100 for "later").
  3. Call project_init with the full feature list. The tool writes feature_list.json, seeds status.json with phase=initialize, and drops template init.sh + verify.yaml.
  4. Customize init.sh via bash_exec (or file_write with the diff path = .agx/project/init.sh):
    • install language runtime / package manager dependencies,
    • apply migrations / generate seed data,
    • must be idempotent (running twice on the same machine should not break anything).
  5. Customize verify.yaml with the project's real test/lint commands. Keep the bootstrap step that runs init.sh.
  6. Smoke-run with verify_run (no feature_id) to confirm the initial gate is green on a clean checkout.
  7. Commit the harness files via bash_exec:
    git add .agx/project init.sh verify.yaml
    git commit -m "chore(project): initialize harness with N features"
    
    Keep this commit small — only harness files, no business code.
  8. Append a closing progress note with progress_append (e.g. "[initialize-done] commit=<sha> features=N") and tell the user the project is ready for a Coding session.

Read the full file on GitHub · 51 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. 2d ago First seen · 51 lines · 34 tokens per session scan A ebe84b87e1d5

Subscribe to this mod's changes

project-initializer is a skill published in the GitHub repository DemonDamon/AgenticX (219 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 620 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 2026-08-30.