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 agents/arkaaiadmin/agentic-memory/test-writergit clone --depth 1 https://github.com/ArkaAiAdmin/Agentic-MemoryWhat 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 | $0.00023 | $0.01876 |
| Opus 5 | $0.00012 | $0.00938 |
| Sonnet 5 | $0.00005 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade C, and why
test-writer scanned grade C with 2 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
env = {k: v for k, v in os.environ.items() if not k.startswith("MEMORY_")} Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test writer for the agentic-memory eval/ suite.
Current state
- 271 test files, 4346+ test functions in
eval/ - Subprocess-per-file runner for torch-safe parallelism
_ProdDBGuardedmixin for tests touching prod DBconftest.pysets env overrides
Test file conventions
- File pattern:
eval/test_<name>.py - Class pattern:
class Test<Name>(unittest.TestCase) - Method pattern:
def test_<descriptive_name>(self) - Use
tmp_pathfixture for test databases - Use
_ProdDBGuardedwhen test needs prod DB access
conftest.py autouse fixtures
| Fixture | Scope | Purpose |
|---|---|---|
_test_session_env |
session | Sets env vars: MEMORY_LLM_EXTRACTION=0, MEMORY_KNOWLEDGE_GRAPH=1, MEMORY_ADAPTIVE_RETENTION=1, MEMORY_QUALITY_GATES=1, MEMORY_WRITE_JOURNAL_ENABLED=0, MEMORY_FAIL_ON_INTEGRITY_DRIFT=0 |
clear_pool_between_tests |
function | Calls connection_pool.clear() before and after each test |
reset_auto_save_state |
function | Resets circuit breaker state, stops leftover daemon |
reset_lazy_config_cache |
function | Clears lazy-getattr cache, unsets MEMORY_RERANKER_DISABLED |
_test_embedding_setup |
session | Opt-in via marker — sets MEMORY_EMBEDDING_BACKEND=sentence-transformers, model intfloat/e5-small-v2 |
temp_db_path |
function | Yields a fully-bootstrapped temp DB via bootstrap_temp_db() |
project_root |
session | Worktree root path |
project_venv_python |
session | Venv Python path |
project_memory_dir |
session | Memory directory path |
Safety wiring (Hard Rule #8)
Tests hitting prod DB MUST use _ProdDBGuarded mixin:
from eval.test_safety_wiring import _ProdDBGuarded
class TestSomething(_ProdDBGuarded, unittest.TestCase):
def test_thing(self):
# This test is guarded against prod DB pollution
...
Test patterns
Unit test with tmp_path
def test_save_creates_markdown(self, tmp_path):
db_path = tmp_path / "test.db"
save_memory(content="test", category="lessons", db_path=db_path)
md_path = tmp_path / "lessons" / "test.md"
assert md_path.exists()
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 · 189 lines · 23 tokens per session scan C 65e616a39866
test-writer is an agent published in the GitHub repository ArkaAiAdmin/Agentic-Memory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 1,876 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.