reconfigure

reconfigure is a skill for Claude Code, Codex from franzos/claude-plugins. It costs 137 tokens per session (1,081 once invoked), scanned A, original, MIT.

A reconfiguration skill for Forseti, a web interface and OIDC front end for the Ory Kratos identity service and Hydra OAuth2 server.

In plain words
What is it for?
Use it to add social login providers, enable Linux login, register OAuth clients, change email settings, enable SAML single sign-on, or adjust related options.
Why use it?
It helps locate the correct configuration area and make targeted changes to an existing deployment.

Skill for Claude CodeCodex

Part of the forseti plugin — 3 skills shipped together

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/franzos/claude-plugins/reconfigure
Any agent
npx skills add franzos/claude-plugins --skill reconfigure
Clone the repo
git clone --depth 1 https://github.com/franzos/claude-plugins

Made for: Claude Code, Codex.

Or install forseti, the plugin that ships this one along with the rest of its 3 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.

agentmods badge for reconfigure

README.md
[![agentmods](https://agentmods.dev/badge/skills/franzos/claude-plugins/reconfigure.svg)](https://agentmods.dev/skills/franzos/claude-plugins/reconfigure)
Your own site
<a href="https://agentmods.dev/skills/franzos/claude-plugins/reconfigure"><img src="https://agentmods.dev/badge/skills/franzos/claude-plugins/reconfigure.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,081 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 $0.00137 $0.01081
Opus 5 $0.00068 $0.00541
Sonnet 5 $0.00027 $0.00216
Haiku 4.5 $0.00014 $0.00108

Measured 4d ago against content hash 17631bb415b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reconfigure 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 4d 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.

plugins/forseti/skills/reconfigure/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reconfiguring Forseti

Reconfiguration is goal-driven: what does the user want to achieve? The right change lives in different places (Forseti's config.toml, Kratos's kratos.yml, Hydra, or the admin UI). Read the relevant docs/operator-guide.md section for the current detail rather than working from memory, and validate before declaring done.

1. Establish the goal and the current state

Ask what the user wants to achieve if it is not already clear. Then locate the deployment: the active config.toml ($FORSETI_CONFIG_PATH), infra/kratos/kratos.yml, infra/hydra/hydra.yml, and how the stack is run (playground compose vs native). Note whether TLS/proxy is in front (it affects callback URLs).

2. Dispatch by goal

Add a social login provider (GitHub, Google, Microsoft, GitLab, Apple, custom OIDC)

Configured in Kratos, not Forseti. In kratos.yml under selfservice.methods.oidc.config.providers[], add an entry: id, provider, client_id, client_secret (via ${ENV} substitution, not inline), mapper_url, and scope. Provide the claim-to-trait mapper as a Jsonnet file under infra/kratos/ (e.g. oidc.github.jsonnet). At the IdP, register the callback as https://<kratos-host>/self-service/methods/oidc/callback/<id>. Forseti auto-renders one "Sign in with X" button per provider (known: github, google, microsoft, gitlab, apple, facebook; unknown ids get a generic icon). See operator-guide §oidc.

Enable Linux / POSIX login

Forseti-native, via the OAuth Device Authorization Grant. Set the [posix] table in config.toml (uid/gid bands, default_shell, home_prefix, free_seats, pam_client_id/pam_client_secret, hydra_issuer). Mint the confidential Hydra device-auth client with forseti posix-init-client. Enroll the host at /admin/hosts (one-time host_id:secret), provision Kratos identities into POSIX accounts at /admin/posix, and install the forseti-unix host client (NSS + PAM + sshd AuthorizedKeysCommand + daemon; also packaged for Guix). Offline passphrase fallback is /settings/offline-access. Free up to free_seats (default 25); more needs a commercial license.

Read the full file on GitHub · 47 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. 4d ago First seen · 47 lines · 0 tokens per session scan A 17631bb415b2

Subscribe to this mod's changes

reconfigure is a skill published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 23d ago), licensed MIT. It adds 137 tokens to every session and 1,081 once invoked, about $0.0007 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.