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/chainloop-dev/chainloop/claude-mdgit clone --depth 1 https://github.com/chainloop-dev/chainloopWhat 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 | $0.03548 | $0.03548 |
| Opus 5 | $0.01774 | $0.01774 |
| Sonnet 5 | $0.00710 | $0.00710 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade B, and why
chainloop CLAUDE.md 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 today.
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.
echo "127.0.0.1 dex" | sudo tee -a /etc/hosts How it starts
The opening of the file, as written. The whole thing — 302 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 (claude.ai/code) when working with code in this repository.
Overview
Chainloop is an open-source evidence store for Software Supply Chain attestations, SBOMs, VEX, SARIF, and other compliance artifacts. The project consists of three main components: a Control Plane (server), Artifact Content Addressable Storage (CAS), and a CLI client.
Architecture
The codebase follows a microservices architecture with three main components and shared libraries:
Control Plane (app/controlplane/)
Main backend service implementing hexagonal architecture:
- API Layer (
./api/): Protobuf definitions and generated gRPC/HTTP services - Server Layer (
./internal/server): HTTP/gRPC servers, middlewares, and request handling - Service Layer (
./internal/service): Protocol buffer service implementations - Business Layer (
./pkg/biz): Core business logic and repository abstractions- Organizations, workflows, attestations, API tokens, groups, projects
- CAS backend management, integrations, user access control
- Policy evaluation and referrer management
- Data Layer (
./pkg/data): Repository implementations using Ent ORM- PostgreSQL with Atlas migrations in
./pkg/data/ent/migrate/migrations/ - Ent schemas in
./pkg/data/ent/schema/
- PostgreSQL with Atlas migrations in
Dependencies: OIDC provider, PostgreSQL, Secret storage (Vault/AWS/GCP/Azure), Artifact CAS Authentication: JWT tokens, OIDC delegation, RBAC with Casbin Key Features: Multi-tenancy, workflow contracts, policy as code, audit logging
Artifact CAS (app/artifact-cas/)
Content Addressable Storage proxy service:
- API Layer (
./api/): gRPC bytestream protocol for efficient streaming - Server Layer (
./internal/server): gRPC server setup and middlewares - Service Layer (
./internal/service): Bytestream, download, resource, and status services - Storage Backends (
pkg/blobmanager/): OCI registry, S3, Azure Blob Storage- Content-addressable storage with SHA256 digests
- Multi-tenant through runtime credential selection
- Immutable artifact storage with digest verification
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.
- today First seen · 302 lines · 3,548 tokens per session scan B 6b0ae701c7d9
chainloop CLAUDE.md is an instructions file published in the GitHub repository chainloop-dev/chainloop (583 stars, last pushed today), licensed Apache-2.0. It adds 3,548 tokens to every session, about $0.0177 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 2026-09-01.
Other instructions, from other repositories
secure-sdlc-agents CLAUDE.md
Instructions for Kaademos/secure-sdlc-agents, covering secure sdlc — multi-agent orchestration, agent roster, lifecycle phases & handoffs, 1. plan and 2. design.
iac-scanner CLAUDE.md
Instructions for alphacrack/iac-scanner, covering claude.md, what this project is, commands, setup and test.
ai-safe2-framework AGENTS.md
AGENTS.md instructions for CyberStrategyInstitute/ai-safe2-framework, covering ai safe² v3.1 agent entry point, start here, version model, normative interpretation and enforcement planes.
controlkeel AGENTS.md
AGENTS.md instructions for aryaminus/controlkeel, covering controlkeel governance, issue and pr quality, planning and architecture, project commands and phoenix v1.8.
sicario-spec AGENTS.md
Instructions for dfirs1car1o/sicario-spec: For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan.
Cybermes AGENTS.md
Instructions for Zyrexnn/Cybermes, covering 🛡️ cybermes master operational directives (agents.md), 1. 🎯 persona & core mission, 2. ⚡ core operational principles, 3. 📁 strict target-scoped workspace & deliverables and mandatory rules for file creation.