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/botzrdev/dreamd/agents-mdgit clone --depth 1 https://github.com/botzrDev/dreamdWhat 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 | $0.15040 | $0.15040 |
| Opus 5 | $0.07520 | $0.07520 |
| Sonnet 5 | $0.03008 | $0.03008 |
| Haiku 4.5 | $0.01504 | $0.01504 |
Grade A, and why
dreamd AGENTS.md scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Copy curl shape from `docs/http-api.md` `POST /api/v1/learn`; set reserved `source_harness` (e.g. `"aider"`). How it starts
The opening of the file, as written. The whole thing — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — dreamd
This file is read by Claude Code, Cursor, Cline, Codex, and other MCP-aware coding agents when working in this repository. It describes what this project builds, how to navigate and work in it, and the conventions that govern the codebase.
What this repo builds
dreamd is a local-first, single-binary memory layer for AI coding agents. Claude Code,
Cursor, Cline, and other MCP-aware harnesses read and write to a shared .agent/ folder
via MCP. What one agent learns, the next already knows. The file system is the source
of truth — plain JSONL and Markdown you can cat, grep, git diff, and hand-edit.
The one job dreamd is hired for: memory continuity across tools. Not a second brain, not an ambient capture product, not a Python framework SDK.
Repository layout
crates/dreamd-core/ Core memory engine: Tantivy BM25 index, salience collector, episodic store, dream cycle WAL. crates/dreamd-cli/ CLI binary: init, mcp, watch, dream, doctor, version. crates/dreamd-protocol/ Shared types: AgentLearning, EventId, HTTP schemas. packages/dreamd-mcp/ Node.js npx shim (dreamd-mcp). Downloads prebuilt binary — no Rust required at runtime. adapters/claude-code/ .mcp.json.example for Claude Code users. adapters/cursor/ .mcp.json.example + .cursor/rules/dreamd-recall.mdc. SPEC.md Implementation-agnostic spec for the .agent/ convention. CONTRIBUTING.md Dev setup, PR workflow, DCO sign-off requirement. SECURITY.md Threat model and disclosure policy. ARCHITECTURE.md Load-bearing engineering decisions for contributors.
Build and test
Requires Rust stable.
cargo build # build all crates
cargo test --workspace # full test suite
cargo clippy --workspace -- -D warnings # lint (CI enforces zero warnings)
cargo bench -p dreamd-core # recall latency benchmarks
scripts/coverage.sh # HTML + lcov coverage report
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 · 525 lines · 15,040 tokens per session scan A d07dfab86da7
dreamd AGENTS.md is an instructions file published in the GitHub repository botzrDev/dreamd (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 15,040 tokens to every session, about $0.0752 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
open-design AGENTS.md
AGENTS.md instructions for nexu-io/open-design, covering directory guide, core documentation index, workspace directories, inactive or placeholder directories and development workflow.
ORG2 AGENTS.md
AGENTS.md instructions for org2AI/ORG2, covering agents.md — agent skill routing for orgii, skill routing table, root-cause-first bug fixing, default delivery flow and ui copy conventions.
flameox AGENTS.md
Instructions for morluto/flameox, covering repository guidelines, product direction, project structure & module organization, build, test, and development commands and coding style & naming conventions.
open-design CLAUDE.md
Claude Code instructions for nexu-io/open-design, a project described as: 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files…
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.
RepoRelay AGENTS.md
Instructions for Lukie-81/RepoRelay, covering reporelay contributor instructions and reporelay handoff.