agentmods.dev

local-env

local-env is a command for Claude Code from mjmorales/claude-prove. It costs 24 tokens per session (680 once invoked), scanned A, original, MIT.

A setup command for connecting a project to a local checkout of claude-prove, a tool whose files and hooks need a machine-specific path.

In plain words
What is it for?
Use it when setting up claude-prove on a machine, writing its local environment settings, and refreshing the links it uses.
Why use it?
It removes the need to enter that path manually in several places and keeps the project’s local configuration connected to the correct checkout.

Command for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the prove plugin — 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server shipped together

not rated 2repo 28d ago A scan 24 tokens original MIT

Good fit Use it when setting up claude-prove on a machine, writing its local environment settings, and refreshing the links it uses.

Compare 6 commands from other repositories ↓
View source ↗ mjmorales/claude-prove
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 mjmorales/claude-prove
Claude Code
/plugin install prove

Made for: Claude Code.

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server.

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 local-env

README.md
[![agentmods](https://agentmods.dev/badge/commands/mjmorales/claude-prove/local-env.svg)](https://agentmods.dev/commands/mjmorales/claude-prove/local-env)
Your own site
<a href="https://agentmods.dev/commands/mjmorales/claude-prove/local-env"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/local-env.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00680
Opus 5 $0.00012 $0.00340
Sonnet 5 $0.00005 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 7d ago against content hash 20ed517b8048, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

local-env 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.

commands/local-env.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prove Local Env

Write this machine's claude-prove checkout path into the env block of .claude/settings.local.json (auto-gitignored, injected by Claude Code into hooks and Bash), and refresh the reference symlink chain .claude/prove-plugin → ~/.claude-prove/latest → checkout.

Why: git-tracked artifacts carry no machine paths — hook commands and CLAUDE.md command examples reference ${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove} (the env block supplies the value), and CLAUDE.md @-references load through the symlink chain (the links supply the path). Each machine sets both here in one step.

Step 1: Detect the checkout

Resolve the plugin checkout directory, first match wins:

  1. $CLAUDE_PLUGIN_ROOT if set and it contains packages/cli/bin/run.ts
  2. $(pwd) if it contains both .claude-plugin/plugin.json and packages/cli/bin/run.ts (you are inside the claude-prove repo itself)
  3. Otherwise ask the user free-form: "Where is your claude-prove checkout?"

Validate the candidate contains packages/cli/bin/run.ts. If not, report the path and ask again — do not write anything.

Step 2: Confirm

AskUserQuestion with header "Local env":

  • question: "Write CLAUDE_PROVE_PLUGIN_DIR=<resolved path> into .claude/settings.local.json? This file is local to this machine and gitignored."
  • "Write it" — proceed
  • "Change path" — ask free-form for the correct checkout path, re-validate, re-confirm

Step 3: Write

claude-prove install local-env --plugin-dir "<resolved path>"

On failure, surface the CLI error verbatim and stop.

Step 4: Verify and repair drift

Run claude-prove install doctor and inspect the three related checks:

  • plugin-dir-env — must PASS now (source process-env or settings.local.json)
  • stable-root — must PASS when CLAUDE.md carries @.claude/prove-plugin/... references (the symlink chain resolves)
  • hook-paths[...] — a WARN mentioning "machine-absolute dev prefix" means .claude/settings.json still carries the pre-portable format

Read the full file on GitHub · 53 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. 7d ago First seen · 53 lines · 24 tokens per session scan A 20ed517b8048

Subscribe to this mod's changes

local-env is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 28d ago), licensed MIT. It adds 24 tokens to every session and 680 once invoked, about $0.0001 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.

Related

Other commands, from other repositories

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens

implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md.

github/spec-kit · 14 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens