What is context-m AGENTS.md?

A set of AGENTS.md instructions for working on CortexM, a memory system for AI agents that stores facts with their sources and history. It documents the project, commands, code style, and tests.

Use it when an agent works on the CortexM Python module, its memory features, servers, or tests. It includes installation, test, lint, and project-structure guidance.

It gives coding agents the project context and repository rules they need before changing code. This reduces guesswork about how to build, test, and format the project.

How ssmurfgg04-gif/context-m configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ssmurfgg04-gif/context-m. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ssmurfgg04-gif/context-m/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ssmurfgg04-gif/context-m

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ssmurfgg04-gif/context-m/agents-md/github.svg)](https://agentmods.dev/instructions/ssmurfgg04-gif/context-m/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ssmurfgg04-gif/context-m/agents-md"><img src="https://agentmods.dev/badge/instructions/ssmurfgg04-gif/context-m/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ssmurfgg04-gif/context-m/agents-md"><img src="https://agentmods.dev/badge/instructions/ssmurfgg04-gif/context-m/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,354 This file is loaded in full into every session.

When invoked 1,354 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01354	$0.01354
Opus 5	$0.00677	$0.00677
Sonnet 5	$0.00271	$0.00271
Haiku 4.5	$0.00135	$0.00135

Measured 8d ago against content hash 0751e5c4508f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-m 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 8d 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.

AGENTS.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical instructions for autonomous coding agents (Codex, Cursor, Aider, Claude Code, Jules, Gemini CLI, etc.). CLAUDE.md at the repo root is a one-line alias to this file — Claude Code's discovery convention. The cross-tool spec is https://agents.md.

Project overview

cortexm is a deterministic neuro-symbolic memory layer for AI agents.

96 bytes per fact on disk; zero LLM call at ingest (μ=0 protocol).
Provenance on every fact (source span, confidence, trigger_source, valid_from / valid_to, BLAKE3 hash chain).
Surface: Reader, Writer, Extractor, Bridge, TraceStore, MemoryPalace, MCP server, REST server, SPARQL endpoint.
Mem0-compatible public surface: from cortexm import Memory.

The Python module is cortexm/ (rename from context_m/ landed in this cycle). A thin context_m.py shim is shipped for backward compat with existing scripts that did from context_m import Memory.

Build and test commands

pip install -e ".[dev]"                    # editable install + dev deps
pytest -x                                  # full suite, fail-fast
pytest tests/test_research_steals.py -k list   # one file / pattern
ruff check . && ruff format --check .      # lint
python -m cortexm.cli --help               # sanity-check the CLI
python -m cortexm.cli doctor                # SIMD kernels, SQLite ver, deps

Tier-1 / Tier-4 benchmark runs (slow, opt-in):

python benchmarks/run_ood_pipeline.py --personas 4 --skip-render --no-enrich --no-judge
python scripts/longmemeval_judge.py
python scripts/run_beam10m_benchmark.py --config all

Code style

Lowercase module names; one module per file; no __init__.py re-exports except the top-level public API in cortexm/__init__.py.
Type hints required on every public function. from __future__ import annotations at the top of every module.
Prefer pathlib.Path over os.path.
Prefer dataclass(slots=True) for value objects.
Never use print() in library code — use logging (stdlib) or the cortexm.metrics counters.
Never catch Exception broadly — name the exception type.
Determinism is a hard contract: any change that introduces nondeterminism (uuid4 tiebreaks, dict-order dependence, RNG without seed) breaks the BEAM-honest protocol and must be reverted.
Every retrieval MUST carry provenance. The RetrievalResult.provenance field is non-optional.

Read the full file on GitHub · 115 lines

Changes

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.

8d ago First seen · 115 lines · 1,354 tokens per session scan A 0751e5c4508f

Subscribe to this mod's changes

context-m AGENTS.md is an instructions file published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,354 tokens to every session, about $0.0068 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.

Memory and context agent-memory bi-temporal chroma context-engineering mcp vector-symbolic-architecture

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

context-m: Instructions file for Codex