uctm-init

uctm-init is a skill for Claude Code from davepoon/buildwithclaude. It costs 58 tokens per session (648 once invoked), scanned A, original, MIT.

An initialization procedure for uc-taskmanager, a project task-management pipeline. It creates a works directory and, with permission, adds the file and command access the agent needs to local settings.

In plain words
What is it for?
Use it when starting uc-taskmanager in a project, especially when the project has not yet been prepared with its works directory and local agent permissions.
Why use it?
It gives a new project the folders and permissions expected by the task pipeline. The permission step asks before changing local configuration.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Part of the uc-taskmanager plugin — 4 skills, 6 agents shipped together

About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,419 stars · on GitHub · buildwithclaude.com

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/davepoon/buildwithclaude/init
Any agent
npx skills add davepoon/buildwithclaude --skill init
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude

Made for: Claude Code.

Or install uc-taskmanager, the plugin that ships this one along with the rest of its 4 skills, 6 agents.

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 uctm-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/davepoon/buildwithclaude/init.svg)](https://agentmods.dev/skills/davepoon/buildwithclaude/init)
Your own site
<a href="https://agentmods.dev/skills/davepoon/buildwithclaude/init"><img src="https://agentmods.dev/badge/skills/davepoon/buildwithclaude/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00058 $0.00648
Opus 5 $0.00029 $0.00324
Sonnet 5 $0.00012 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured yesterday against content hash 80dda3fa8ed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

uctm-init scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"Bash(curl:*)"
plugins/agents-uc-taskmanager/skills/init/SKILL.md · 96 lines

What it actually says

uc-taskmanager Init

Initialize the current project for uc-taskmanager pipeline execution.

Steps

1. Create works/ directory

if works/ does not exist:
  create works/
  report: ✓ works/ directory created
else:
  report: - works/ already exists

2. Configure Bash Permissions

Ask the user first: "에이전트에 필요한 Bash 권한을 .claude/settings.local.json에 자동 설정할까요? (recommended) [Y/n]"

If the user approves (or says yes/Y/확인):

Read .claude/settings.local.json (create if not exists). Merge the following permissions into permissions.allow array — skip any that already exist (do not duplicate):

[
  "Read(/**)",
  "Edit(/**)",
  "Write(/**)",
  "Read(**)",
  "Edit(**)",
  "Write(**)",
  "Bash(ls:*)",
  "Bash(cat:*)",
  "Bash(mkdir:*)",
  "Bash(basename:*)",
  "Bash(find:*)",
  "Bash(wc:*)",
  "Bash(sort:*)",
  "Bash(tail:*)",
  "Bash(head:*)",
  "Bash(echo:*)",
  "Bash(printf:*)",
  "Bash(grep:*)",
  "Bash(sed:*)",
  "Bash(cut:*)",
  "Bash(tr:*)",
  "Bash(node:*)",
  "Bash(npm run:*)",
  "Bash(npm test:*)",
  "Bash(bun run:*)",
  "Bash(yarn:*)",
  "Bash(cargo:*)",
  "Bash(go build:*)",
  "Bash(go test:*)",
  "Bash(python:*)",
  "Bash(ruff:*)",
  "Bash(make:*)",
  "Bash(git:*)",
  "Bash(curl:*)"
]

Preserve any existing entries in permissions.allow and permissions.deny — only add missing ones.

if permissions added:
  report: ✓ {N} permissions added to .claude/settings.local.json (total: {T})
else if skipped by user:
  report: - Skipped permission setup
else:
  report: - All permissions already configured

3. Summary

After all steps, show a summary:

uc-taskmanager initialized!

  ✓ works/ directory ready
  ✓ Bash permissions configured

  Next: Type [new-feature] Add a hello world feature

Arguments

$ARGUMENTS

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. yesterday First seen · 96 lines · 58 tokens per session scan A 80dda3fa8ed2

Subscribe to this mod's changes

uctm-init is a skill published in the GitHub repository davepoon/buildwithclaude (3,419 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 648 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

aidd-dev:08:for-sure

Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.

ai-driven-dev/framework · 66 tokens

06-product-brief

Produces a concise Product Brief before requirements. Use when the user wants to frame or revisit a product opportunity and how it will be validated. Not for requirements, technical design, or planning.

ai-driven-dev/framework · 42 tokens

bun-test-mocking

Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.

secondsky/claude-skills · 25 tokens

api-response-optimization

Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.

secondsky/claude-skills · 36 tokens

domain-model

Creates or modifies domain types in src/domain/ — value objects, discriminant unions, and aggregate roots. Use when adding a new domain concept, defining invariants for an existing type, or placing a shared discriminant union that is used across multiple use-cases. Do NOT use for orchestrating I/O or business logic …

ai-driven-dev/framework · 88 tokens

aidd-async-dev:02:run

Runs one async development pipeline cycle: polls ready GitHub issues, resolves dependencies, locks the issue, delegates implementation to whichever SDLC capability is loaded at runtime, then writes audit log and SIEM webhook. Use when the user (or CI / cron / @claude mention / project board move) says "run async dev"…

ai-driven-dev/framework · 0 tokens