A repository setup process that scans a code project and creates devcontainer profiles. A devcontainer is a defined development environment that runs separately from the host computer.

Use it when a repository lacks an isolation profile or needs one updated, especially before isolated development or brainstorming workflows.

It records how the project should be worked on and provides isolated environments for repeatable runs. It also checks existing toolchains, CI setup, forge hosting, and credential patterns before asking questions.

fr-init — Skill for Claude Code and Codex by derio-net: A repository setup process that scans a code project…

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/derio-net/super-fr/fr-init

Any agent

npx skills add derio-net/super-fr --skill fr-init

Clone the repo

git clone --depth 1 https://github.com/derio-net/super-fr

Made for: Claude Code, Codex.

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/derio-net/super-fr/fr-init.svg)](https://agentmods.dev/skills/derio-net/super-fr/fr-init)

Your own site

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

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,493 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.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.01493
Opus 5	$0.00045	$0.00746
Sonnet 5	$0.00018	$0.00299
Haiku 4.5	$0.00009	$0.00149

Measured 5d ago against content hash 4a2ce0737043, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fr-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 5d 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.

.hermes/skills/fr/fr-init/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fr-init

Captures "how you work in this repo" as committed devcontainer profiles plus host-only secrets placeholders. Interactive BY DESIGN — the interview is operator-owned context, so this skill is exempt from autonomy contracts: under a fr-goal run, a missing devcontainer is a blocker; pause, run this interview, resume isolated.

Announce at start: "I'm using fr-init to set up this repo's profiles."

1. Scan first

Before asking anything, learn what the repo already says:

Languages and toolchains: manifests (pyproject/package.json/go.mod/...), lockfiles, .tool-versions, CI workflows (what does CI install?).
Existing .devcontainer/ (profiles already present? then this is an edit, not a green-field init). Check .devcontainer/fr-profiles.yaml for an existing top-level backend:/host: key too.
Which forge: git remote get-url origin's hostname (github.com / gitlab.com self-identify; anything else, including a literal gitea.com, is self-hosted and needs the operator to confirm the backend explicitly — no hostname alone distinguishes GitLab Self-Managed / Gitea / GitHub Enterprise).
Credential surface: .env* patterns in .gitignore, CI secret names, cloud/k8s configs — candidates for the profile's expected secrets.
Working patterns: Makefile/justfile/scripts (what do humans run here?).

The interview confirms and fills gaps; it never asks what the scan answers.

2. Interview (AskUserQuestion, batched ≤4 per round)

Cover, with scan-informed recommended options:

Backend — github (default), gitlab, or gitea? Skip asking if the scan already resolved it unambiguously (github.com/gitlab.com remote, or an explicit backend: key already in fr-profiles.yaml). Confirm the hostname too (--host) if self-hosted — drives which CLI (gh/glab/tea) gets installed and which CI template fr acceptance init picks.
Profiles wanted — one dev default, or split (e.g. readonly for review/exploration vs admin with deploy credentials)? Profiles differ by CREDENTIALS first, tools second — same binaries, different env-files is the normal shape.
Tools — confirm the scan's toolchain list; surface what CI installs that local work also needs (kubectl, terraform, docker-in-docker...).
Credentials per profile — which env KEYS each profile expects (names only, never values). Do NOT ask for a host-forge token by default: push, PR/MR creation, and every fr-driven gh/glab/tea call run on the authenticated HOST (fr-isolation's credential boundary) — the container needs none for the standard pipeline. Offer it only for an explicit in-container-writes profile (e.g. admin).
Working patterns — test/build/run commands worth recording in the profile's purpose/notes so future runs know the repo's verbs.

Read the full file on GitHub · 121 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

.source 119 B

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.

5d ago First seen · 121 lines · 90 tokens per session scan A 4a2ce0737043

Subscribe to this mod's changes

fr-init is a skill published in the GitHub repository derio-net/super-fr (1 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,493 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.

Containers DevOps and cloud agent-skills ai-agents automation claude-code claude-code-plugin devcontainers

fr-init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

fr-init

1. Scan first

2. Interview (AskUserQuestion, batched ≤4 per round)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

deploy

cloudflare-sandbox

symfony:runner-selection

deploy-mcp

branchbox-devcontainer-guardrails

container-execution