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/sabbour/agentweaver/agents-mdgit clone --depth 1 https://github.com/sabbour/agentweaverWhat 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 | $0.00448 | $0.00448 |
| Opus 5 | $0.00224 | $0.00224 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
agentweaver 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.
What it actually says
AGENTS.md
Agentweaver is developed with Squad, a team of named AI agents (Trinity, Tank,
Morpheus, Smith, Link, Seraph, Scribe, and others), and welcomes contributions from AI
agents — including GitHub's @copilot coding agent. If you are an AI agent (Copilot,
Claude, Cursor, or any other tool) that just cloned this repo, start here.
Process
CONTRIBUTING.md → "AI agent contributions"
is the full process doc — read it before making changes. It covers the issue-driven
lifecycle (issue → branch → PR → review → merge), the label-based Squad automation, the
reviewer-rejection protocol, rubber-ducking, the auditable decisions inbox
(.squad/decisions/inbox/), and docs-as-you-go (docs are part of the definition of done,
not a follow-up). This file is a pointer, not a replacement — don't skip the source.
For the dev → release → main model and release/maintenance branching, see
CONTRIBUTING.md → "Branch Topology".
Build & test
The exact per-area build/test commands live in
CONTRIBUTING.md → "Testing" (and are mirrored by the CI
workflow). Run only the suite(s) relevant to what you changed; use the commands there
rather than guessing, so the two don't drift.
Other key docs
RELEASING.md— versioning (semver), branching model, and how a release differs from a deploy/upgrade.specs/README.md— the current product-spec index (area-grouped product stories) for product/feature context..github/copilot-instructions.md— the Copilot-specific version of this orientation.
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 · 34 lines · 448 tokens per session scan A 333eafc6d905
agentweaver AGENTS.md is an instructions file published in the GitHub repository sabbour/agentweaver (5 stars, last pushed 2d ago), licensed MIT. It adds 448 tokens to every session, about $0.0022 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
nora CLAUDE.md
Instructions for solomon2773/nora, covering claude.md, what this repo is, development commands, docker compose (primary path) and per-service dev (without docker).
janus-mcp CLAUDE.md
Claude Code instructions for tonylchang/janus-mcp, covering claude.md, what janus is, commands, architecture and testing conventions.
agentic-operator-core CLAUDE.md
Claude Code instructions for Clawdlinux/agentic-operator-core, covering agentic operator core and writing style (applies to all output).
agentcontrolplane CLAUDE.md
Claude Code instructions for humanlayer/agentcontrolplane, covering agent control plane (acp) - ai assistant instructions, 🚨 the 1500-line minimum read rule - this is not optional, 📋 your 20-point todo list - you need this structure, current todo list (you must maintain 20+ items) and 🚨 mandatory persona selection.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.