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.
npx agentmods add instructions/backchainai/backchain-plugins/claude-mdgit clone --depth 1 https://github.com/backchainai/backchain-pluginsWhat 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 | $0.00770 | $0.00770 |
| Opus 5 | $0.00385 | $0.00385 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
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.
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 relativesourcepaths 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-invocationdecides who may invoke a skill.truemeans only the operator can, via/<skill-name>; Claude never loads it automatically and never preloads it into a subagent. The defaultfalselets Claude invoke it when the description matches the conversation. Settruefor a skill whose timing the operator controls, as theadvisorsskills do. Leave itfalsefor a routing skill that has to fire on its own trigger context. Omitting the field is the same asfalse:diogenes/skills/auditomits it deliberately, because its description is written to auto-trigger.
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.
- 2d ago First seen · 48 lines · 770 tokens per session scan A a97df2eedfbb
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.
Other instructions, from other repositories
agentic-context-engine AGENTS.md
Instructions for kayba-ai/agentic-context-engine, covering agents.md, repository guidelines, pipeline-first development (mandatory), core code protection and documentation maintenance.
graymatter AGENTS.md
Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.
graymatter CLAUDE.md
Instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.
mnemon AGENTS.md
Instructions for mnemon-dev/mnemon, covering mnemon agent guidelines, development, go engineering and commit discipline.
mnemon CLAUDE.md
Instructions for mnemon-dev/mnemon, covering mnemon — project guidelines and development.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.