A project setup command that creates Shield’s configuration file and working folders, while checking for older plugin setups that may need migration.

Use it when starting Shield in a repository, choosing the project and output settings, checking for required tools, and optionally migrating old configuration.

It gives the other commands a known project configuration and output location, and helps avoid losing existing planning artifacts during setup.

init — Command for Claude Code by infraspecdev/tesseract

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add infraspecdev/tesseract

Claude Code

/plugin install shield

Made for: Claude Code.

Or install shield, the plugin that ships this one along with the rest of its 36 skills, 17 commands, 22 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/infraspecdev/tesseract/init/github.svg)](https://agentmods.dev/commands/infraspecdev/tesseract/init)

Your own site

<a href="https://agentmods.dev/commands/infraspecdev/tesseract/init"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/init/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/infraspecdev/tesseract/init"><img src="https://agentmods.dev/badge/commands/infraspecdev/tesseract/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,463 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.01463
Opus 5.5	$0.00008	$0.00585
Sonnet 5.5	$0.00004	$0.00293
Haiku 4.5	$0.00002	$0.00146

Measured 1mo ago against content hash 699c8e8f329c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

init scanned grade C with 2 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 1mo 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

[y] Run: curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

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

[y] Run: curl -LsSf https://astral.sh/uv/install.sh | sh

shield/commands/init.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shield Init

Set up Shield for this project. If this is a fresh setup, create configuration from scratch. If old plugins are detected, suggest running /shield migrate instead.

Steps

Check for existing setup
- If .shield.json already exists, show current config and ask if user wants to reconfigure
- If old plugin config is detected (sprint-planner.json, claude/infra-review/), suggest /shield migrate instead
- If shield/plan.json exists (old single-plan path), offer to migrate it to {output_dir}/{feature}/plans/ — derive name from the project or phase field in the JSON

1a. Check runtime dependencies (uv)

Run command -v uv to detect uv. If found, skip this step.
If missing, tell the user: "Shield uses uv to run two things on demand: the PRD HTML renderer (every /prd), and the PM adapter MCP servers (every /pm-sync, if configured). uv is not currently on your PATH."

Offer to install it now:

Install uv automatically? (y/n)
  [y] Run: curl -LsSf https://astral.sh/uv/install.sh | sh
  [n] Skip — Shield will still init, but /prd will fail until uv is installed

If user says yes:
- Run the installer via Bash: curl -LsSf https://astral.sh/uv/install.sh | sh
- Confirm: command -v uv (the installer adds ~/.local/bin to PATH for new shells; in the current shell, prefix with export PATH="$HOME/.local/bin:$PATH" for the verification)
- Tell the user: "uv installed at ~/.local/bin/uv. New terminal sessions will pick it up automatically."

If user says no, continue with init but record this — at step 8 (summary), include a clear warning:

⚠ uv not installed. /prd will fail when rendering prd.html.
  Install when ready: curl -LsSf https://astral.sh/uv/install.sh | sh

Gather project info
- Ask for project name (default: repo directory name)
- Ask for output directory (default: docs/shield). This is where all Shield artifacts go.
- Ask for active domains — show available options:
  - terraform — Terraform/HCL infrastructure
  - atmos — Atmos stack management
  - github-actions — CI/CD workflows
  - (more domains in future)
- Allow multiple selections
- Ask about reviewer preferences (optional):
  - auto_select — auto-pick reviewers based on content (default: true)
  - always_include — reviewers that always run (e.g., ["security"])
  - never_include — reviewers to skip

Read the full file on GitHub · 123 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.

1mo ago First seen · 123 lines · 20 tokens per session scan C 699c8e8f329c

Subscribe to this mod's changes

init is a command published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,463 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Project management

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

fest-show

Show festival progression (in-progress tasks, roadmap, and dependency view).

Obedience-Corp/festival · 17 tokens

add-note

Add an internal or external note to a ConnectWise PSA ticket.

WYRE-AI/msp-claude-plugins · 12 tokens

sync-linear

Sync current work with Linear ticket status.

bybren-llc/safe-agentic-workflow · 0 tokens

dispatcher

Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…

Kanevry/session-orchestrator · 185 tokens

workpm

A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.

Dannykkh/skill-olympus · 31 tokens

init