What is cli CLAUDE.md?

A set of instructions for working on Archgate, a command-line tool that turns architecture decisions into documents and machine-checkable rules.

It guides development and verification of the Bun and TypeScript CLI, including linting, type checks, tests, formatting, dead-code checks, and architecture-record checks.

It defines the project's technologies, commands, formatting, tests, build checks, and required validation so changes can be checked consistently.

cli CLAUDE.md — Instructions file by archgate

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 instructions/archgate/cli/claude-md

Clone the repo

git clone --depth 1 https://github.com/archgate/cli

Per session 2,551 This file is loaded in full into every session.

When invoked 2,551 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.02551	$0.02551
Opus 5	$0.01275	$0.01275
Sonnet 5	$0.00510	$0.00510
Haiku 4.5	$0.00255	$0.00255

Measured yesterday against content hash 2304e95dea83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli CLAUDE.md 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 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.

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.

CLAUDE.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Archgate is a CLI tool for AI governance via Architecture Decision Records (ADRs) — combining human-readable docs with machine-checkable rules. The CLI dogfoods itself via ADRs in .archgate/adrs/. AI features are delivered as a Claude Code plugin (../plugins/claude-code), not via direct API calls.

Technology Stack

Runtime: Bun — not Node.js compatible (minimum version enforced in src/cli.ts)
Language: TypeScript (strict mode, ESNext, ES modules)
CLI framework: Commander.js (@commander-js/extra-typings)
Linter: Oxlint | Formatter: Oxfmt | Dead exports: Knip | Commits: Conventional Commits

Commands

bun run src/cli.ts <command>  # run CLI locally
bun run lint                  # oxlint
bun run typecheck             # tsc --build
bun run format                # oxfmt --write
bun run format:check          # oxfmt --check
bun run test                  # all tests (not bare `bun test` — picks up --timeout; see GEN-003)
bun run knip                  # dead export detection
bun run validate              # MANDATORY: lint + typecheck + format:check + test + ADR check + knip + build check
bun run build:check            # verify build compiles (CI builds binaries via release workflow)
bun run commit                # conventional commit wizard

Validation Gate

bun run validate must pass before any task is considered complete. Fail-fast pipeline: lint → typecheck → format:check → test → ADR check → knip → build check. Mirrors CI in .github/workflows/code-pull-request.yml.

Git Hooks (Git 2.54+)

Config-based hooks in .githooks run validation locally before commits and pushes:

pre-commit: lint + typecheck + format:check (~15s)
pre-push: full bun run validate (~60s, mirrors CI)

Activate once per clone:

git config --local include.path ../.githooks

Opt out of a specific hook: git config --local hook.<name>.enabled false. Skip all hooks for a single commit: git commit --no-verify.

Read the full file on GitHub · 120 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.

yesterday First seen · 120 lines · 2,551 tokens per session scan A 2304e95dea83

Subscribe to this mod's changes

cli CLAUDE.md is an instructions file published in the GitHub repository archgate/cli (64 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,551 tokens to every session, about $0.0128 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.

Git and workflow Planning Testing adr architecture bun claude-code cli cursor

cli CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Technology Stack

Commands

Validation Gate

Git Hooks (Git 2.54+)

What this file has done since we first saw it

Other instructions, from other repositories

mcp-adr-analysis-server copilot-instructions.md

coderadius AGENTS.md

adrkit copilot-instructions.md

adrkit CLAUDE.md

ai-software-architect AGENTS.md

open-sunsama AGENTS.md