Borrowing it
Nothing to install: this file belongs to agentic-box/memora. 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/agentic-box/memora/main/AGENTS.mdgit clone --depth 1 https://github.com/agentic-box/memoraWrote 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/agentic-box/memora/agents-md)<a href="https://agentmods.dev/instructions/agentic-box/memora/agents-md"><img src="https://agentmods.dev/badge/instructions/agentic-box/memora/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/agentic-box/memora/agents-md"><img src="https://agentmods.dev/badge/instructions/agentic-box/memora/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00997 | $0.00997 |
| Opus 5.5 | $0.00399 | $0.00399 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
memora 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in memora
memora is a SQLite-backed memory server (MCP + a plain HTTP API). Read
README.md for behaviour, docs/ for subsystem design, and
contracts/memora-api/v1/README.md for the API contract.
Running tests
- Install the dev extras once:
pip install -e '.[dev]'. - Run targeted tests, not the whole suite:
python -m pytest -q <files>. The full suite is the leader's to run, once per candidate commit. - Run a passing candidate on a Linux build host (
<build-host>; venvs~/verify/venv312and the 3.10 floor~/verify/venv310) and on the Mac test host (<mac-test-host>). CI's floor is Python 3.10 (see.github/workflows/clean-install.yml); a change must pass there. tests/test_no_infra_identifiers.pyscansgit ls-files, so it needs a real git checkout — run it from a worktree, never from an extracted tarball.- Graph UI changes (
memora/graph/**,memora-graph/**) are covered bymemora-graph/scripts/test_ui.mjs(thegraph-uiCI job), not pytest. - Before a review request, run only the tests you added or changed. After a PASS, run the targeted set plus a mutation (make each claimed test fail once). See the sealed-review skill.
Touched module → test file
Tests are named after their subject. Start from the map below, then add every test file that imports the touched module.
| Touched | Test file(s) |
|---|---|
memora/<x>.py |
tests/test_<x>.py when it exists |
memora/api_v1.py, api_absorb.py |
tests/test_api_v1.py, tests/test_api_absorb.py, tests/test_api_contract.py |
memora/graph/** |
tests/test_graph_server.py, memora-graph/scripts/test_ui.mjs |
contracts/memora-api/v1/** |
tests/test_api_contract.py |
scripts/deploy*, Dockerfile |
tests/test_deploy_memora_all.py, tests/test_deploy_config.py |
scripts/<x>.py, scripts/<x>.sh |
tests/test_<x>.py where one exists (e.g. mint_api_token.sh → tests/test_mint_api_token.py) |
scripts/add_store.sh, scripts/add_store_config.py |
tests/test_add_store.py |
memora/add_store.py, local_primary.py bootstrap-d1 / pre-freeze / clear-freeze |
tests/test_add_store_bootstrap.py |
memora/copy_memories.py, scripts/copy_memories.py |
tests/test_copy_memories.py |
scripts/memora_api_contract.py |
tests/test_api_contract.py |
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 · 70 lines · 997 tokens per session scan A 5991a3e813ab
memora AGENTS.md is an instructions file published in the GitHub repository agentic-box/memora (746 stars, last pushed yesterday), licensed MIT. It adds 997 tokens to every session, about $0.0040 per session on Opus 5.5. 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 2026-10-28.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.