rembric: Skill for Claude Code

.agents/skills/rembric-plugin-development/SKILL.md

rembric-plugin-development is a skill for Claude Code from susomejias/rembric. It costs 110 tokens per session (3,074 once invoked), scanned B, original, MIT.

A set of instructions for developing and reviewing Rembric plugins, which are add-ons that connect Rembric agents to coding tools.

In plain words
What is it for?
Use it when creating or changing Rembric plugins, adding support for coding-agent clients, or reviewing plugin-related files.
Why use it?
It helps keep plugin code, release versions, client integrations, and design documents aligned as the plugin changes.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

This is susomejias/rembric's own configuration. It tells Claude Code how to work on rembric itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rembric configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to susomejias/rembric. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/susomejias/rembric/main/.agents/skills/rembric-plugin-development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/susomejias/rembric

Made for: Claude Code.

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 rembric-plugin-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/susomejias/rembric/rembric-plugin-development/github.svg)](https://agentmods.dev/skills/susomejias/rembric/rembric-plugin-development)
Your own site
<a href="https://agentmods.dev/skills/susomejias/rembric/rembric-plugin-development"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/rembric-plugin-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rembric-plugin-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/susomejias/rembric/rembric-plugin-development"><img src="https://agentmods.dev/badge/skills/susomejias/rembric/rembric-plugin-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.03074
Opus 5 $0.00055 $0.01537
Sonnet 5 $0.00022 $0.00615
Haiku 4.5 $0.00011 $0.00307

Measured 11d ago against content hash 6e9ad9ed089b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

rembric-plugin-development scanned grade B with 1 finding 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 11d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **`chmod 644` for files invoked as `node <path>`** (the +x bit isn't needed for `node x.mjs`).
.agents/skills/rembric-plugin-development/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rembric plugin development

Authoritative specs: openspec/specs/{claude-code-plugin,codex-distribution,hermes-agent-plugin,opencode-plugin,pi-plugin,plugin-session-protocol}/. Archived decisions: openspec/changes/archive/.

Mandatory workflow

  1. OpenSpec change first. Run /opsx:propose (or amend an existing change). Plugin work always touches ≥2 specs and ≥3 files. Skipping the change is the failure mode that produces drift.
  2. Two release tracks: server + unified plugin (no cascade). release-please runs exactly two components, no node-workspace/linked-versions/grouping. server (apps/server, package @rembric/server, tag server-v*) builds the Docker image. plugin (apps/plugin — the WHOLE tree, no exclude-paths, package @rembric/plugin, tag plugin-v*) carries one unified version for all five clients; its extra-files update every client carrier in lock-step (.claude-plugin/{package,plugin}.json, .codex-plugin/{package,plugin}.json, .hermes-plugin/plugin.yaml, .opencode-plugin/plugin.ts comment, .pi-plugin/package.json). A change to ANY plugin file bumps the single plugin version — claude/codex/opencode/hermes/pi never diverge; the CHANGELOG (scoped by conventional commit) records what actually changed. A plugin release NEVER rebuilds the server image (publish-docker gates on server_release_created), but it IS what publishes @rembric/pi to npm (trusted-publishing OIDC, provenance, no long-lived token). .pi-plugin/ has to live inside apps/plugin/ for that: release-please attributes a release by the paths of the commits under the component's path, so a client outside it would never cause a release and its carrier would only move when something unrelated did. release-please.yml carries a concurrency guard (cancel-in-progress: false) so a rapid second merge can't cancel tag-minting. The former six-component + node-workspace cascade was retired (change unify-plugin-release-track) after its anchor-tag fragility produced phantom release PRs. Legacy per-client tags (claude-code-plugin-v*, …) stay in history, inert.
  3. End-to-end against pnpm run dev:docker:up before reporting done — see E2E discipline below.
  4. Docs sweep: README.md, docs/agents.md, apps/plugin/README.md, the in-plugin README.md, apps/plugin/CHANGELOG.md. New-client checklist in references/files-checklist.md.

Read the full file on GitHub · 107 lines

Files

What ships with it

2 files 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.

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. 11d ago First seen · 107 lines · 110 tokens per session scan B 6e9ad9ed089b

Subscribe to this mod's changes

rembric-plugin-development is a skill published in the GitHub repository susomejias/rembric (12 stars, last pushed 8d ago), licensed MIT. It adds 110 tokens to every session and 3,074 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.