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/earendil-works/absurd/agents-mdgit clone --depth 1 https://github.com/earendil-works/absurdWhat 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 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
absurd 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 yesterday.
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
Absurd is a Postgres-native durable workflow system. It moves the complexity of durable execution into the database layer via stored procedures, keeping SDKs lightweight and language-agnostic. The core principle is to handle tasks that may run for minutes, days, or years without losing state.
Key concept: A task is subdivided into steps that act as checkpoints.
Tasks can suspend (for sleep or events) and resume without data loss. All state
lives in Postgres tables prefixed by queue name (t_, r_, c_, e_, w_).
Repository Structure
- sql/absurd.sql - Core Postgres schema and stored procedures. This is the heart of the system.
- sdks/typescript/ - TypeScript SDK (
absurd-sdkon npm) - habitat/ - Go-based web UI for monitoring tasks, runs, and events
- absurdctl - Python-based CLI tool for queue/task management and debugging
- tests/ - Python test suite using psycopg and testcontainers
Building and Testing
TypeScript SDK
cd sdks/typescript
npm install
npm run build # Compiles to dist/ (both ESM and CommonJS)
Habitat (Web UI)
cd habitat
make build # Build UI + Go binary -> bin/habitat
make dev # Run dev server with hot reload
./bin/habitat run -db-name your-database-name
Python Tests
cd tests
uv run pytest # Run all tests
uv run pytest test_foo.py # Run single test file
Formatting
make format # Format TypeScript SDK, habitat UI, and Python tests
Habitat Web UI
Habitat connects directly to Postgres and serves a SolidJS dashboard. It shows task state, run history, checkpoint data, and events. Useful for debugging and monitoring.
Configuration via flags or HABITAT_* env vars (see habitat/README.md).
Additional Information
More information can be found in @README.md and @CONTRIBUTING.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.
- yesterday First seen · 60 lines · 479 tokens per session scan A c0d1091c7a78
absurd AGENTS.md is an instructions file published in the GitHub repository earendil-works/absurd (2,394 stars, last pushed 21d ago), licensed Apache-2.0. It adds 479 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.