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/opencoven/psyche-build/agents-mdgit clone --depth 1 https://github.com/OpenCoven/psyche-buildWhat 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 | $0.01643 | $0.01643 |
| Opus 5 | $0.00822 | $0.00822 |
| Sonnet 5 | $0.00329 | $0.00329 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
psyche-build 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Psyche Build agent guide
This file applies to the entire repository. A more specific AGENTS.md may narrow these rules for its subtree. Human instructions and repository policy take precedence over this guide.
Repository role
Psyche Build is OpenCoven's coding cockpit and product client. It owns user-facing cockpit behavior and product-local composition around projects, panes, terminals, tmux sessions, worktrees, branches, optional provider integrations, and platform clients.
Psyche Build does not own the durable OpenCoven identity or orchestration protocol:
OpenCoven/psycheowns canonical familiar, task, lane, run, lease, approval, action, receipt, recovery, and compatibility semantics.- The Coven daemon owns process and PTY execution, project-boundary enforcement, and authoritative runtime events.
- Psyche Build consumes those contracts through versioned adapters. It must not direct-read Psyche's database, duplicate canonical protocol state, or infer authority/completion from a UI selection, tmux pane, process, path, worktree, branch, provider session, Bead, or GitHub issue.
- Issue #253 owns the future immutable Psyche profile pin and compatibility canary. Until that lands, do not claim Psyche protocol conformance.
Planning and evidence contract
| Surface | Owns | Must not become |
|---|---|---|
| GitHub issues and milestones | Public outcomes, owners, acceptance gates, and externally legible status | A duplicate implementation dependency graph or runtime identity model |
| Beads | Internal implementation tasks and dependency ordering | Familiar, task, run, lane, action, or receipt identity |
| Pull requests | Reviewable implementation slices and exact-head proof | Evidence that an entire user path works merely because unit tests pass |
| Specs and plans | Design intent, decisions, and historical reasoning | Executable backlog or proof that behavior shipped |
| Acceptance records | Runtime observations tied to immutable source and artifacts | Unbounded logs, screenshots without provenance, or maintainer memory |
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 · 105 lines · 1,643 tokens per session scan A c565bfab7047
psyche-build AGENTS.md is an instructions file published in the GitHub repository OpenCoven/psyche-build (2 stars, last pushed 2d ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0082 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
flow CLAUDE.md
Instructions for AixleHQ/flow, covering claude.md, documentation index, before pushing a branch or opening/updating a pr, docker is required and test parallelization.
agent-os CLAUDE.md
Instructions for earthwalker17/agent-os, covering claude.md, 1. project mission, 2. core architecture principles, 3. agent roles and main agent (orchestrator).
nori-skillsets AGENTS.md
Instructions for tilework-tech/nori-skillsets, covering plugin package changes, claude code configuration vs. nori plugin package, skills documentation, style guide and functions and named parameters.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
copperhead CLAUDE.md
Instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).
seektty AGENTS.md
Instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.