A setup tool that creates an optional .ai/swe.json file in a repository. The file stores local preferences for how coding agents should collaborate on that project.

Running a short preference interview or quick setup, creating repository-local agent settings, and configuring collaboration defaults for later SWE skills.

It gives later agent workflows a small, project-specific set of working preferences without changing the project's runtime or installing dependencies.

swe:init — Skill for Claude Code by ckorhonen

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.

Any agent

npx skills add ckorhonen/swe-skills --skill init

Clone the repo

git clone --depth 1 https://github.com/ckorhonen/swe-skills

Made for: Claude Code.

Or install swe-skills, the plugin that ships this one along with the rest of its 17 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/swe-skills/init.svg)](https://agentmods.dev/skills/ckorhonen/swe-skills/init)

Your own site

<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/init"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,906 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.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.01906
Opus 5	$0.00048	$0.00953
Sonnet 5	$0.00019	$0.00381
Haiku 4.5	$0.00010	$0.00191

Measured 7d ago against content hash e0e2c844d36e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

swe:init 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.

skills/init/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE Init

What This Skill Does

Use this skill to establish an optional repo-local preference layer for how agents should collaborate in a specific repository.

The job is to:

gather a short set of behavior-shaping preferences
write them to .ai/swe.json as minified JSON
keep the file local-first while allowing the user to commit it if they want
define how later skills should consult the file safely

This skill is not a general repository bootstrapper. It configures agent collaboration defaults, not the project's runtime or package setup.

When To Use

Use this skill when the user wants to:

initialize repo-local agent settings
create a small preference file for how agents should work in this repo
run a quick-start setup with opinionated defaults
make later swe: skills respect local collaboration preferences

Do Not Use

Do not use this skill for:

npm init, pnpm init, or similar project scaffolding
dependency installation or toolchain bootstrap
.env, secret, or credential setup
committed team policy unless the user explicitly wants the file checked in
broad repo documentation or agent-guidance rewrites unrelated to the local preference layer

Inputs To Confirm

Confirm or infer:

whether the user wants full interview mode or quick mode
whether .ai/swe.json already exists
whether .gitignore should be updated
whether any sensitive paths should trigger extra caution

If the user asks for quick mode, skip the interview entirely.

If .ai/swe.json already exists, do not overwrite it silently. Ask whether the user wants to keep it, edit it, or replace it.

Preference Contract

The preference file path is fixed:

.ai/swe.json

The file format is fixed:

minified JSON
include "v": 1
store only values that differ from the built-in defaults
keep keys compact but legible

Use this schema:

v: schema version
autonomy: bounded, ask, or assertive
plan: minimal, short, or design
scope: minimal, balanced, or broad
verify: narrow, standard, or broad
report: terse, evidence, or full
alts: material or usually
paths: array of sensitive path strings

Read the full file on GitHub · 283 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.

7d ago First seen · 283 lines · 97 tokens per session scan A e0e2c844d36e

Subscribe to this mod's changes

swe:init is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,906 once invoked, about $0.0005 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.

Claude Code agent-skills claude-plugins codex

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.