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 shawnhack/exocortex --skill publicgit clone --depth 1 https://github.com/shawnhack/exocortexWrote 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/shawnhack/exocortex/public)<a href="https://agentmods.dev/skills/shawnhack/exocortex/public"><img src="https://agentmods.dev/badge/skills/shawnhack/exocortex/public/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/shawnhack/exocortex/public"><img src="https://agentmods.dev/badge/skills/shawnhack/exocortex/public.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 | $0.00000 | $0.00478 |
| Opus 5.5 | $0.00000 | $0.00191 |
| Sonnet 5.5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
public 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
exocortex
Persistent long-term memory for AI agents. Store, search, and reason over knowledge that persists across sessions. Semantic search, knowledge graphs, temporal reasoning, and self-improving retrieval.
Tools
Core
memory_store— Store knowledge with content, tags, importance (0-1), tier, namespacememory_search— Hybrid search (vector + FTS + graph). Use expanded_query for better recall, compact for token efficiencymemory_get— Fetch full memory content by IDmemory_context— Load broad context for a topic. Use deep=true for LLM-driven iterative retrievalmemory_update— Update memory content, tags, importance, or metadatamemory_forget— Soft-delete a memory
Intelligence
memory_project_snapshot— Project context: goals, decisions, threads, techniquesmemory_contradictions— Find contradictory facts in stored knowledgememory_timeline— Track topic evolution over timememory_diff— Compare memory state between time periods
Knowledge Graph
memory_entities— Browse extracted entities (people, projects, tech)memory_graph— Entity relationship graph with centrality scoresmemory_link— Create explicit connections between memories
Ingestion
memory_ingest— Ingest documents/URLs with automatic chunkingmemory_research— Web research with automatic knowledge storage
Goals & Predictions
goal— Track goals with milestones and progressprediction— Make and resolve predictions for calibration
Usage Pattern
Session start:
memory_contextwith topic → load relevant backgroundmemory_project_snapshot→ goals, decisions, open threads
During work:
3. memory_search for specific knowledge retrieval
4. memory_store to persist decisions, discoveries, techniques
Session end: 5. Store session summary and key learnings
Authentication
Set auth.token in DB settings. Pass via Authorization: Bearer <token> or X-Exocortex-Token.
Links
- REST: http://localhost:4010
- MCP: stdio transport
- Dashboard: http://localhost:4010 (web UI)
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.
- 1mo ago First seen · 54 lines · 0 tokens per session scan A 08d13b9ee729
public is a skill published in the GitHub repository shawnhack/exocortex (1 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 478 tokens. 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.
Other skills, from other repositories
grounded-knowledge-workflow
Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…
velesdb-memory
Use durable, explainable, self-improving memory across a coding session via the velesdb-memory MCP server. Trigger whenever the velesdb-memory MCP tools (remember/recall/recallfused/relate/why/feedback/forget/rememberextracted/extractionstatus/entity/memorystatus) are available and the work would benefit from…
velesdb-learning-loop
Turn every velesdb design / implement / verify cycle into durable, connected memory so the SAME mistake is never repeated and later decisions build on what was already learned, instead of re-deriving it or silently colliding with it. Trigger BEFORE starting a design or implementation on velesdb / velesdb-core /…
ragcode-memory
Manage shared cross-AI memories for this project through RagCode MCP tools (memorywrite, memoryquery, memorylist, memorydelete), with ragcode memory CLI fallback when MCP is unavailable. Read prior decisions, user preferences, and feedback written by other AI agents, and record new insights so they persist across…
mindmap-brainstorm
Brainstorm an idea with your portable Mind Map memory so a thread you start in one AI tool continues in another. Use when the user wants to brainstorm, ideate, "think through", or explore options/approaches/ideas — especially when the topic may have prior history in another tool or session. Loads prior idea-threads…
trailmem
Use when saving or recalling persistent memory via trailmem MCP tools (trailmemstore, trailmemquery, trailmemwelcome, ...), when a trailmem tool call fails or is rejected, or when unsure how to fill its parameters (project scoping, agenttype, eventtype, dedup, linking, archiving).