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/eric-tramel/moraine/agents-mdgit clone --depth 1 https://github.com/eric-tramel/moraineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/eric-tramel/moraine/agents-md)<a href="https://agentmods.dev/instructions/eric-tramel/moraine/agents-md"><img src="https://agentmods.dev/badge/instructions/eric-tramel/moraine/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.02733 | $0.02733 |
| Opus 5 | $0.01367 | $0.01367 |
| Sonnet 5 | $0.00547 | $0.00547 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
moraine AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS "http://127.0.0.1:${port}/api/v1/health" How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a Rust workspace for local Moraine services and shared libraries.
apps/: binary crates (moraine,moraine-ingest,moraine-monitor,moraine-mcp).crates/: shared libraries (config, ClickHouse client, ingest/monitor/MCP core logic).sql/: ordered schema and migration SQL (001_...sql,002_...sql, etc.).config/: default runtime/config templates (moraine.toml, ClickHouse XML).scripts/: CI helpers, packaging, docs tooling.docs/: MkDocs source; generated site output goes tosite/.web/monitor/: static monitor UI assets served by monitor service.
Prefer adding new runtime logic under apps/ + crates/ (not legacy rust/ or moraine-monitor/ paths).
Build, Test, and Development Commands
cargo build --workspace --locked: build all workspace crates.cargo test --workspace --locked: run unit/integration tests across workspace.cargo fmt --all -- --check: enforce formatting (matches CI).bash scripts/ci/e2e-stack.sh: run functional stack + MCP smoke test.bin/moraine up/bin/moraine status/bin/moraine down: local stack lifecycle.make install: build the current checkout for the host target and install it over the activemoraineon your PATH (release bundle → the samescripts/install.shpath users get; ClickHouse skipped by default,INSTALL_ARGS="--with-clickhouse"to include it). Use this to test tip-of-branch on the host instead of waiting for a tagged release. Seescripts/dev/install-host.sh --help.make docs-build/make docs-serve: MkDocs build/serve.make hooks-install: enable the repo-managed git hooks (.githooks/pre-commitrunscargo fmt --checkand the same clippy strict baseline CI uses). One-time per clone; bypass a single commit withSKIP_PRECOMMIT=1 git commit ...orgit commit --no-verify.make agent-plugins-install: register the Codex Moraine marketplace from the configuredmainbranch and install/update themoraine-devcontributor workflow plugin. UseAGENT_PLUGINS_SOURCE=currentonly when testing unmerged plugin changes from the current checkout.
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.
- 5d ago First seen · 146 lines · 2,733 tokens per session scan A 4e12f2739b5b
moraine AGENTS.md is an instructions file published in the GitHub repository eric-tramel/moraine (116 stars, last pushed 18d ago), licensed Apache-2.0. It adds 2,733 tokens to every session, about $0.0137 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 2026-08-30.
Other instructions, from other repositories
keyword-rag-mcp CLAUDE.md
Claude Code instructions for cskwork/keyword-rag-mcp, covering claude.md, project overview, core architecture, key components and development commands.
cs CLAUDE.md
Claude Code instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
Xapiand AGENTS.md
Instructions for Kronuz/Xapiand, covering agents.md — working in the xapiand codebase, first, the big split: own code vs. vendored, where things live, build & toggles and verifying changes end-to-end (the docs are a test suite).
ketch CLAUDE.md
Claude Code instructions for 1broseidon/ketch, covering ketch, architecture, build & test, output format and output flags (all commands).
memex AGENTS.md
AGENTS.md instructions for nicosuave/memex, covering agents and before committing.
neurodivergent-memory copilot-instructions.md
Instructions for jmeyer1980/neurodivergent-memory, covering neurodivergent-memory — agent bootstrap instructions, what this server is, canonical tag schema, districts and available mcp tools (quick reference).