mongez-agent-kit-cli-usage

A command reference for agent-kit's init, sync, and watch commands, plus their programmatic equivalents. It explains the available options and how the commands behave when run repeatedly.

In plain words
What is it for?
Use it to initialize a project, sync agent files and skills, watch for development changes, select target agents, and run operations from scripts.
Why use it?
It provides the exact commands for creating instruction files, synchronizing skills, and monitoring changes without guessing the required flags.

Skill for Claude CodeCodex

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/hassanzohdy/agent-kit/cli-usage
Any agent
npx skills add hassanzohdy/agent-kit --skill cli-usage
Clone the repo
git clone --depth 1 https://github.com/hassanzohdy/agent-kit

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,866 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01866
Opus 5 $0.00020 $0.00933
Sonnet 5 $0.00008 $0.00373
Haiku 4.5 $0.00004 $0.00187

Measured yesterday against content hash 9dce42593cb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mongez-agent-kit-cli-usage 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.

skills/cli-usage/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-kit CLI usage

Three commands. All are idempotent — running them twice in a row is a no-op the second time.

agent-kit init

Scaffold a starter AGENTS.md (only if it does not exist), derive the per-tool files from it, and seed agentKit.targets in package.json.

npx @mongez/agent-kit@latest init                 # no install — runs the latest published version
npx @mongez/agent-kit@latest init --target claude,cursor

Scoped name with npx. Use npx @mongez/agent-kit … (scoped) when running without a local install — npx agent-kit … (unscoped) resolves a different package. The bare agent-kit binary only works once it's installed locally.

Flags:

  • --cwd <path> — start from a different working directory (defaults to process.cwd()).
  • --target <names> — comma-separated skill targets to write into package.json's agentKit.targets (claude, copilot, cursor, codex, opencode, amp, goose, kiro, antigravity). Defaults to claude. Passing this overwrites an existing agentKit.targets; without it, an already-set value is left alone. Unknown names error out before anything is written.

init vs sync — different delivery

  • init is a one-time scaffold → npx @mongez/agent-kit@latest init is ideal (zero install, always latest).
  • sync runs on every install and in CI → install agent-kit as a pinned dev dependency and call it from postinstall. Don't route the recurring sync through always-latest npx — a new agent-kit version could silently change generated output, breaking build reproducibility. Ad-hoc manual npx @mongez/agent-kit@latest sync is fine.

Behavior:

  • If AGENTS.md exists → leave it alone.
  • If AGENTS.md is missing → write a starter template.
  • Always derives CLAUDE.md, .gemini/GEMINI.md, .github/copilot-instructions.md, CONVENTIONS.md.
  • Seeds agentKit.targets into package.json: writes ["claude"] (the built-in default, made explicit so it's discoverable and editable) when no agentKit.targets exists; writes --target's value when that flag is passed, overwriting any existing list. An existing agentKit block's other fields (pick, omit, …) and the file's indentation are preserved. Note targets only gates the skills export — init itself doesn't sync skills, so the seeded value first takes effect on the next agent-kit sync.
  • Wires "postinstall": "agent-kit sync" into package.json — but only when it's safe: (1) @mongez/agent-kit is already a declared dependency/devDependency (so the bare agent-kit binary resolves at install time — the npx @mongez/agent-kit@latest init bootstrap installs nothing, so wiring a postinstall there would break the next install), and (2) no postinstall already exists (an existing one is never clobbered). When either gate blocks, init prints a hint instead of writing.

Read the full file on GitHub · 131 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. yesterday First seen · 131 lines · 40 tokens per session scan A 9dce42593cb6

Subscribe to this mod's changes

mongez-agent-kit-cli-usage is a skill published in the GitHub repository hassanzohdy/agent-kit (2 stars, last pushed 15d ago), licensed MIT. It adds 40 tokens to every session and 1,866 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens