backchain-plugins CLAUDE.md

Repository instructions for Backchain's Claude Code plugin marketplace, a collection of add-ons for Claude Code.

In plain words
What is it for?
Use them when changing plugin manifests, skills, scripts, documentation, or evaluation projects and when running the repository's checks.
Why use it?
They explain the marketplace layout, validation checks, plugin structure, and conventions used by its projects.

Instructions file

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 instructions/backchainai/backchain-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/backchainai/backchain-plugins
Per session 770 This file is loaded in full into every session.
When invoked 770 The same file — it is already loaded in full.
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 $0.00770 $0.00770
Opus 5 $0.00385 $0.00385
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 2d ago against content hash a97df2eedfbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backchain-plugins CLAUDE.md 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.

CLAUDE.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.

Repository Overview

A Claude Code plugin marketplace by Backchain, published at backchainai/backchain-plugins. Skills and manifests are markdown and JSON, and some skills ship executable payload alongside them. scripts/gates/structure.sh runs the structural gate, which discovers and runs the tracked stdlib python test suites shipped alongside skill scripts; claude plugin validate . runs the lint gate. Most plugins' evals/ directories are uv projects with their own pyproject.toml and lockfile.

Plugins

  • advisors — Decision analysis advisory panel (Team of Rivals)
  • engram — Filesystem-backed agent memory (consolidate, briefing, working)
  • diogenes — AI-slop content audit (senior-reviewer subagent)
  • brief — Interactive HTML briefs for plans, specs, and decisions
  • scriptorium — Diataxis-grounded documentation authoring and placement (docs skill)

Architecture

.claude-plugin/marketplace.json    # Marketplace manifest (name: backchain-plugins)
scripts/gates/                     # Structural gate + its self-test (structure.sh, test_structure.sh)
advisors/
  .claude-plugin/plugin.json       # Plugin manifest
  skills/
    advisor-*/SKILL.md             # Four individual advisor skills
    advisory-panel/SKILL.md        # Panel orchestration skill

Key patterns

  • Marketplace manifest (marketplace.json) uses relative source paths to reference plugins. Each plugin is a self-contained directory.
  • Plugin manifests (plugin.json) declare plugin metadata, discoverability fields, and components.
  • Skills use YAML frontmatter per the agentskills.io spec. disable-model-invocation decides who may invoke a skill. true means only the operator can, via /<skill-name>; Claude never loads it automatically and never preloads it into a subagent. The default false lets Claude invoke it when the description matches the conversation. Set true for a skill whose timing the operator controls, as the advisors skills do. Leave it false for a routing skill that has to fire on its own trigger context. Omitting the field is the same as false: diogenes/skills/audit omits it deliberately, because its description is written to auto-trigger.

Read the full file on GitHub · 48 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 · 48 lines · 770 tokens per session scan A a97df2eedfbb

Subscribe to this mod's changes

backchain-plugins CLAUDE.md is an instructions file published in the GitHub repository backchainai/backchain-plugins (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 770 tokens to every session, about $0.0038 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.