Borrowing it
Nothing to install: this file belongs to pyranthus-hq/mora. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pyranthus-hq/mora/main/AGENTS.mdgit clone --depth 1 https://github.com/pyranthus-hq/moraWrote 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/pyranthus-hq/mora/agents-md)<a href="https://agentmods.dev/instructions/pyranthus-hq/mora/agents-md"><img src="https://agentmods.dev/badge/instructions/pyranthus-hq/mora/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 5.1 | $0.00842 | $0.00842 |
| Opus 5 | $0.00421 | $0.00421 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
mora 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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Mora
Cross-tool guidance for AI agents and reviewers (any tool that reads AGENTS.md).
The deep architecture spec lives in docs/architecture/
— read the overview first; this file adds the review rules enforced on PRs.
What Mora is
Local-first, agent-agnostic memory CLI: one pure-Go binary that stores
human-readable Markdown memories, indexes them in embedded SQLite, and serves
them to any MCP agent. Read-only connectors (Gmail, Calendar, iMessage, WhatsApp), zero
egress. See the README for orientation, docs/guide.md
for every command and connector, and docs/architecture/
for the subsystem spec.
Review guidelines
When reviewing a PR, focus on the diff and report only material issues
(P0/P1). Skip style nits — gofmt, go vet, and golangci-lint are
deterministic CI gates and already own formatting. Cap findings; be terse.
Hard rules — flag any violation as blocking:
- No import cycle:
internal/google(and every connector package) must NOT importinternal/mora. Connectors return plainMappedMemorystructs;morawires them at the boundary. New connectors follow the same rule and live ininternal/<provider>, importing onlyinternal/memory. - Pure Go, no CGO: the product must build with
CGO_ENABLED=0. No C extensions (nosqlite-vecC ext), nomattn/go-sqlite3—modernc.org/sqliteonly. The race detector in CI (CGO_ENABLED=1) is test-only and never affects the release build. - Read-only + zero egress: Google scopes stay
gmail.readonly/calendar.readonly. iMessage openschat.dband WhatsApp opens onlyChatStorage.sqlitewithmode=ro(neverimmutable=1; never open WhatsApp'sAxolotl.sqlitekey store); Apple Calendar opens its live WAL store with a hierarchicalfile:URI,mode=ro, andquery_only(1)(neverimmutable=1, which can ignore live changes). No connector writes to its source; no telemetry/egress. MCP mutations are separately governed bymcp_write_policy: initialization text and dispatch authority must agree;proposenever writes the vault before local approval and never stages destructive deletes;readonlyrefuses both mutation tools. - Honest-snapshot sync: never swallow sync errors — surface them
(freshness is the product's value).
Retrieval may surface a newer strongly-related record, but must call it
later_related_evidence, never infer “superseded” or “closed.” Only an explicit Teach governance decision may assert supersession. - State vs vault: usage logging and sync cursors live in the state dir,
never the vault. Honor
DO_NOT_TRACK/mora usage off. - Identity vs filename:
StableIDis provider identity only (gmail_thread/<id>), never content; files are named withSafeFilename(/→_). Any ID lookup must match the SafeFilename form. - Dependency hygiene: don't
go mod tidybetween adding a dep and its first import (tidy prunes unimported requires). Don't add a dependency without a clear need; prefer the standard library. - Secrets:
internal/google/client.jsonis a committed NON-SECRET placeholder. Real credentials come fromMORA_GOOGLE_CREDENTIALSat runtime — never commit real creds.
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.
- 7d ago First seen · 59 lines · 842 tokens per session scan A 4ed841228454
mora AGENTS.md is an instructions file published in the GitHub repository pyranthus-hq/mora (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 842 tokens to every session, about $0.0042 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
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.
vscode buildNext.instructions.md
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
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
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.
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
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.