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/holsee/conjure/agents-mdgit clone --depth 1 https://github.com/holsee/conjureWhat 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 | $0.02530 | $0.02530 |
| Opus 5 | $0.01265 | $0.01265 |
| Sonnet 5 | $0.00506 | $0.00506 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade B, and why
conjure AGENTS.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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Skills can execute arbitrary code - audit before loading How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for LLM coding agents working on this repository.
Project Overview
Conjure is an Elixir library for Anthropic Agent Skills with Claude models. It provides:
- Unified Session API -
Conjure.Session.chat/3works across all backends - 4 Execution Backends - Local, Docker, Anthropic (hosted), Native (BEAM)
- Skill Loading - Parse SKILL.md files with YAML frontmatter, load
.skillZIP packages - Pluggable Storage - Local, S3, Tigris backends for session file management
- API-Agnostic - No HTTP client bundled; consumers provide API callbacks
Build & Development Commands
# Install dependencies
mix deps.get
# Run tests
mix test
mix test path/to/test.exs # Specific file
mix test path/to/test.exs:42 # Specific line
# Code quality (all enforced in CI)
mix format # Auto-format
mix format --check-formatted # Check formatting
mix credo --strict # Lint
mix dialyzer # Type checking
mix compile --warnings-as-errors # Strict compilation
# Full CI check locally
mix format && mix credo --strict && mix compile --warnings-as-errors && mix test && mix dialyzer
# Generate documentation
mix docs
Architecture
Module Hierarchy
Conjure (Main API)
├── Session (Unified interface)
│ └── Backend (Behaviour)
│ ├── Local (System.cmd execution)
│ ├── Docker (Container execution)
│ ├── Anthropic (Skills API)
│ └── Native (BEAM execution)
├── Loader (SKILL.md parsing)
├── Registry (GenServer skill store)
├── Storage (Behaviour)
│ ├── Local (Temp directories)
│ ├── S3 (AWS)
│ └── Tigris (Fly.io)
└── NativeSkill (Behaviour for Elixir skills)
Key Modules
| Module | Purpose |
|---|---|
Conjure |
Main public API entry point |
Conjure.Session |
Unified session interface, delegates to backends |
Conjure.Backend |
Behaviour defining unified interface for all backends |
Conjure.NativeSkill |
Behaviour for implementing skills as Elixir modules |
Conjure.Storage |
Behaviour for session storage backends |
Conjure.Loader |
SKILL.md parsing, ZIP loading, progressive disclosure |
Conjure.Registry |
GenServer-based skill registry with hot-reload |
Conjure.Conversation |
Tool-use conversation loop (Local/Docker) |
Conjure.Prompt |
Generates XML-formatted system prompt fragments |
Conjure.Tools |
Claude-compatible tool schemas (view, bash_tool, create_file, str_replace) |
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 · 347 lines · 2,530 tokens per session scan B c912075562d4
conjure AGENTS.md is an instructions file published in the GitHub repository holsee/conjure (10 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 2,530 tokens to every session, about $0.0127 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.