edit

A command for changing the skills, agents, origins, and scopes installed in the current setup. It can use an interactive wizard or apply a configuration shared from agentsinc.sh.

In plain words
What is it for?
Use it to edit the local configuration, open the browser-based editor with --ui, or apply a shared configuration with --from.
Why use it?
It provides one place to update an installation and shows which items were added, removed, or changed.

Command

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 commands/agents-inc/agents-inc/edit
Clone the repo
git clone --depth 1 https://github.com/agents-inc/agents-inc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,512 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 $0.00000 $0.10512
Opus 5 $0.00000 $0.05256
Sonnet 5 $0.00000 $0.02102
Haiku 4.5 $0.00000 $0.01051

Measured 2d ago against content hash bf601e181bb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

edit 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 2d 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.

packages/cli/.ai-docs/reference/commands/edit.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Edit Command (Detailed)

Extracted from: reference/commands/index.md (edit section) and reference/type-system.md (edit command types). See commands/index.md for the full commands reference.

File: src/cli/commands/edit.tsx

Purpose: Modify what is installed here, from one of two producers — the wizard, or a configuration shared from agentsinc.sh — and apply the difference. Outputs a styled change summary (chalk-colored +/-/~ lines for added/removed/changed skills, agents, origins, scopes) and a simplified completion message ("Done"). Change summary uses skill display names (from matrix) and scope labels ([G]/[P]). Global-to-project scope changes render as green + additions.

edit is also the one command that stands on both ends of the editor round trip: --ui mints an id for this installation and opens it in the browser, --from <id> applies a configuration back. The wire contract behind both is features/seed-contract.md.

Flags

static flags declares three flags — two public, one hidden.

Flag Type Hidden Description
--ui boolean no default: false. Opens agentsinc.sh instead of the wizard — the id --from names, or this installation when --from names nothing.
--from string no helpValue: "<id>". Apply a configuration shared from agentsinc.sh by its id, removing whatever it leaves out. Interactive and destructive — see below.
--project-setup boolean yes Internal: this run continues an init project setup (materialise + register even on no-change). Key = EDIT_PROJECT_SETUP_FLAG ("project-setup"); set only by init's dashboard delegation.

Read the full file on GitHub · 363 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. 2d ago First seen · 363 lines · 0 tokens per session scan A bf601e181bb9

Subscribe to this mod's changes

edit is a command published in the GitHub repository agents-inc/agents-inc (8 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 10,512 tokens. 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.