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 skills add julymetodiev/post-cortex --skill post-cortex-memorygit 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/skills/julymetodiev/post-cortex/post-cortex-memory)<a href="https://agentmods.dev/skills/julymetodiev/post-cortex/post-cortex-memory"><img src="https://agentmods.dev/badge/skills/julymetodiev/post-cortex/post-cortex-memory/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/skills/julymetodiev/post-cortex/post-cortex-memory"><img src="https://agentmods.dev/badge/skills/julymetodiev/post-cortex/post-cortex-memory.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 | $0.00194 | $0.02602 |
| Opus 5.5 | $0.00078 | $0.01041 |
| Sonnet 5.5 | $0.00039 | $0.00520 |
| Haiku 4.5 | $0.00019 | $0.00260 |
Grade A, and why
post-cortex-memory 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
post-cortex memory
post-cortex keeps a durable, searchable memory of a project: every entry is a typed record (a decision, a fixed problem, a code change, ...) linked into an entity graph, and every entry is embedded for semantic search. It only pays off if you read before you answer and write after you learn. Memory that is never searched is dead weight; memory that is never written is empty.
1. Find the session first
Every read and write is scoped to a session_id (a UUID). Sessions are usually grouped in a workspace (workspace_id) so related repos or sub-projects can be searched together. Resolve them once at the start and reuse them:
- Look in the project's
CLAUDE.md/AGENTS.md(or the injected context from hooks) for a session ID and workspace ID.pcx setupwrites them there. - Otherwise
sessionwithaction: "search"and the project or repo name asquery, oraction: "list"to see all. - Only if nothing fits, create one:
sessionaction: "create"with a descriptivenameanddescription, thenmanage_workspaceaction: "create"(orlistto reuse one) andadd_sessionwithrole: "primary". Tell the user the new IDs so they can be written into the project instructions — otherwise the next session cannot find them.
Do not invent IDs or reuse IDs from another project: writes go to the wrong place silently.
2. Read before answering
Search when the answer might already exist: architecture and "why is it like this" questions, anything about past decisions, a bug that looks familiar, a task the user describes as continuing earlier work. A cheap search beats re-deriving (or contradicting) a decision that is already on record.
Narrow-to-wide is the default because the closest scope has the most relevant hits:
semantic_search(query, scope="session", scope_id=<session_id>)
→ too few / weak hits → scope="workspace", scope_id=<workspace_id>
→ still nothing → scope="global"
Write queries as natural-language questions or the key terms of what you need ("why did we switch the embedding model", "SurrealDB schema migration"), not single words. Useful knobs:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +8 lines 43e706ef3261
- 3d ago First seen · 115 lines · 194 tokens per session scan A 4bf3446c5472
post-cortex-memory is a skill published in the GitHub repository julymetodiev/post-cortex (20 stars, last pushed yesterday), licensed MIT. It adds 194 tokens to every session and 2,602 once invoked, about $0.0008 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 2026-10-19.
Other skills, from other repositories
using-axon
Use when operating an installed Axon through its MCP tool or CLI to search, index sources, query the corpus, extract data, manage jobs or watches, and troubleshoot the RAG stack. For first-time setup or deployment repair, use install-axon.
data-sync
Sync and archive data from messaging platforms (WhatsApp, Discord, Slack, Twitter/X, Google) into Moltis memory as daily digest summaries. Orchestrates crawl tools and writes structured markdown to the memory system.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…