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/0xdarkmatter/conclave/agents-mdgit clone --depth 1 https://github.com/0xDarkMatter/conclaveWhat 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 | $0.01268 | $0.01268 |
| Opus 5 | $0.00634 | $0.00634 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
conclave AGENTS.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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding assistants working on Conclave.
Project Overview
Conclave is a Go CLI that queries multiple LLM providers in parallel and synthesizes their responses. It operates in two modes:
- CLI Mode (default): Wraps provider CLIs (
gemini,claude,codex, etc.). Exception:glmcalls the Z.ai Coding Plan over HTTP directly (no CLI binary) — see ADR-007. - API Mode (
-g): Direct API calls to providers
Architectural decisions are recorded in
docs/adr/(the directory is the index). Runpython ~/.claude/skills/adr-ops/scripts/adr-touching.py <path>to find which ADR governs a file before changing it.
Architecture
cmd/
root.go # Main CLI entry, flag parsing, orchestration
init.go # Interactive API key setup
internal/
config/ # Configuration loading (.env, config.yaml)
context/ # File/stdin context building
judge/ # Verdict synthesis logic
orchestrator/ # Parallel provider execution
output/ # Result formatting (JSON, human, brief)
progress/ # Terminal progress display
providers/ # Provider implementations
provider.go # Provider interface
registry.go # Provider registration and lookup
gemini.go # CLI provider
api_gemini.go # API provider
...
Key Conventions
Provider Pattern
Each provider implements the Provider interface:
type Provider interface {
Name() string
DefaultModel() string
IsAvailable() bool
Query(ctx context.Context, prompt string, model string) (string, time.Duration, *Metrics, error)
}
- CLI providers wrap external commands (
gemini.go,claude.go) and embedbaseProvider - API providers make HTTP calls (
api_gemini.go,api_anthropic.go) and embedapiBaseProvider - Exception:
glm.gois a CLI-mode provider that embedsapiBaseProvider(HTTP to the Coding Plan endpoint, no binary) — ADR-007
Adding a New Provider
- Create
internal/providers/{name}.go(CLI) and/orapi_{name}.go(API) - Implement the
Providerinterface - Register in
AllCLIProviders()orAllAPIProviders()inregistry.go - Add to
providerSetupInfoincmd/init.gofor interactive setup - Update tests in
provider_test.go - Document in
README.mdanddocs/MODEL_REGISTRY.md
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 · 145 lines · 1,268 tokens per session scan A 40a6648d8d82
conclave AGENTS.md is an instructions file published in the GitHub repository 0xDarkMatter/conclave (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,268 tokens to every session, about $0.0063 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
ima2-gen AGENTS.md
Instructions for lidge-jun/ima2-gen, covering ima2-gen — ai context, what this project does, tech stack, project structure and agent skills (packaged).
deliberation CLAUDE.md
Instructions for antonbabenko/deliberation, covering claude.md, what this is, development commands, test plugin locally (loads from working directory) and run setup to test installation flow.
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
ThreadShelf AGENTS.md
Instructions for ChrystianSchutz/ThreadShelf, covering agents.md, what this project is, repository layout, commands and conventions.
deep-research AGENTS.md
Instructions for u14app/deep-research, covering agents.md, 🚀 development workflow & commands, core commands, testing and 📂 project structure.