pickfit

BrowseDeveloper CLIs

Actual.ai CLI

CLI that answers architecture questions from ADRs and writes agent context files.

Tested on macOS and LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 4 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:zip 2.4.2 zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE (GHSA-m665-v7pm-7grj, critical, fixed in 9.0.5)
See 3 more

macOS arm64

You need first

  • Keys or accounts: Actual AI account
  1. brew install actual-software/actual/actual

    brew install actual-software/actual/actual
Where the README and reality differ
  • README: actual adr-bot --dry-run works with no account or API key (ADR-backed context needs no account or API key)
    What worked: needs a runner (claude-cli or ANTHROPIC_API_KEY); without it exits 2 with No runner available

Check that it works

actual --version 2>&1

The output should contain “actual 0.11.0”.

First thing to try

mkdir -p /tmp/test-adr && cd /tmp/test-adr && git init -q && git config user.email "test@test.com" && git config user.name "test" && echo "# test" > README.md && git add . && git commit -qm init && echo done && ls -la
cd /tmp/test-adr && actual advisor "Should new services talk over gRPC or REST?" 2>&1

Run actual advisor "<your question>" inside a repository to ask an architecture question.

Linux x86_64

You need first

  • Keys or accounts: Actual AI account
  1. install actual CLI via npm

    npm install -g @actualai/actual
Where the README and reality differ
  • README: actual adr-bot --dry-run preview without writing
    What worked: install a runner (e.g. npm install -g @anthropic-ai/claude-code) or set ANTHROPIC_API_KEY/OPENAI_API_KEY; without it adr-bot --dry-run exits 2 with No runner available
  • README: actual rules ls list rule documents
    What worked: rule bullets must be - **<id>** LEVEL: text (e.g. - **cache-redis** MUST: ...); without it rules ls reports no parseable Rules and plan-check finds no rules

Check that it works

actual --version

The output should contain “actual 0.10.0”.

First thing to try

mkdir -p /tmp/actual-test && cd /tmp/actual-test && git init -q 2>&1; echo "# test repo" > README.md; echo "console.log('hi')" > app.js; git add . 2>&1; git -c user.email=test@test.com -c user.name=test commit -qm init 2>&1; pwd; ls -la; git log --oneline | cat
cd /tmp/actual-test && actual status 2>&1

Run actual advisor "<your question>" inside a repository to ask an architecture question.

What it does

  • Ask architecture questions answered from your ADRs
    Not tested
  • Write ADR guidance to agent context files
    Not tested
  • Check plans and changes against architecture rules
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Good for

  • Ask an architecture question grounded in team ADRs
  • Preview ADR guidance for a repository
  • Write ADR-based context to CLAUDE.md
  • Check an agent plan against architecture rules
  • Check working tree changes against architecture rules

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

macOS arm64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.11.0

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version actual 0.10.0

Differences the test machine hit

  • README: actual plan-check --plan-file plan.md
    In the test: actual plan-check with a matching rule and no runner exits 0 with Could not check: no runner available (documented not_checked outcome, only conflicting exits non-zero)

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.