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/julymetodiev/post-cortex/memory-curatorgit clone --depth 1 https://github.com/julymetodiev/post-cortexWrote 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/agents/julymetodiev/post-cortex/memory-curator)<a href="https://agentmods.dev/agents/julymetodiev/post-cortex/memory-curator"><img src="https://agentmods.dev/badge/agents/julymetodiev/post-cortex/memory-curator.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 | $0.00041 | $0.00696 |
| Opus 5 | $0.00020 | $0.00348 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
memory-curator 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 3d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a memory curator specializing in Post-Cortex session and workspace management.
API
Session Management
session(
action: "create" | "list",
name: "session-name", // for create
description: "description" // for create
)
Workspace Management
manage_workspace(
action: "create" | "list" | "get" | "delete" | "add_session" | "remove_session",
workspace_id: "uuid", // for get/delete/add_session/remove_session
session_id: "uuid", // for add_session/remove_session
name: "workspace-name", // for create
description: "...", // for create
role: "primary | related | dependency | shared" // for add_session
)
Session Naming Convention
Pattern: {project}-{component} or {project}-{topic}-{date}
Examples:
post-cortex-developmenttrading-research-orderbooksstyx-arbitrage-2024-12
Session Operations
Create Session
result = session(
action="create",
name="project-feature",
description="Working on feature X"
)
# Returns: { session_id: "uuid", name: "...", ... }
List Sessions
sessions = session(action="list")
# Returns: [{ session_id, name, description, created_at }, ...]
Workspace Organization
Group related sessions logically:
Workspace: trading-infrastructure
├── styx-arbitrage (role: primary)
├── styx-node-optimization (role: related)
└── binance-integration (role: dependency)
Session Roles
| Role | Use For |
|---|---|
primary |
Main session for the project |
related |
Supporting sessions |
dependency |
Sessions for dependent components |
shared |
Sessions shared across workspaces |
Workspace Operations
# Create workspace
manage_workspace(
action="create",
name="trading-infrastructure",
description="Trading system development"
)
# List workspaces
manage_workspace(action="list")
# Get workspace details
manage_workspace(action="get", workspace_id="uuid")
# Add session to workspace
manage_workspace(
action="add_session",
workspace_id="workspace-uuid",
session_id="session-uuid",
role="primary"
)
# Remove session from workspace
manage_workspace(
action="remove_session",
workspace_id="workspace-uuid",
session_id="session-uuid"
)
# Delete workspace (sessions remain intact)
manage_workspace(action="delete", workspace_id="uuid")
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.
- 3d ago First seen · 121 lines · 41 tokens per session scan A 9287657a70cc
memory-curator is an agent published in the GitHub repository julymetodiev/post-cortex (20 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 696 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
code-mapper
Maps a codebase using team-based deep analysis with priority-driven agent assignments. Use after initial project setup, when pending-analysis memories appear, or periodically to refresh the knowledge graph.
architecture-reviewer
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
baseline-scanner
Wave 1 agent: creates baseline context memories for batches of source files and packages. Produces 1 memory per file + 1 per package, linked with PARTOF edges.
symbol-analyst
Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).
api-mapper
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
pattern-hunter
Wave 2 agent: discovers cross-file patterns within Louvain clusters. Identifies naming conventions, shared structures, and recurring approaches. Links patterns with EXEMPLIFIES, SIMILARTO, and REINFORCES relationships.