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 AdityaVG13/cortex --skill recallgit clone --depth 1 https://github.com/AdityaVG13/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/adityavg13/cortex/recall)<a href="https://agentmods.dev/skills/adityavg13/cortex/recall"><img src="https://agentmods.dev/badge/skills/adityavg13/cortex/recall/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/adityavg13/cortex/recall"><img src="https://agentmods.dev/badge/skills/adityavg13/cortex/recall.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 | $0.00034 | $0.00410 |
| Opus 5.5 | $0.00014 | $0.00164 |
| Sonnet 5.5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
recall 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 28d 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.
What it actually says
Cortex Recall
Search your persistent memory for relevant past knowledge. Cortex uses Clock-Quorum Recall: it admits a stored row when a path, symbol, alias, entity, stem, or closed-lexicon handle matches — not because a sentence is “nearby” in embedding space. An empty result means there was no shared handle. That is expected. Narrow with a path, symbol, or quoted phrase rather than rephrasing into vaguer English.
Usage
/cortex:recall <query>
The $ARGUMENTS placeholder contains your search query.
Budget Guidance
Cortex adapts detail level to token budget:
| Query Type | Budget | Detail Level |
|---|---|---|
| Specific lookup | 200 | Balanced - key facts + context |
| Broad exploration | 500 | Full detail - complete entries |
| Quick check | 0 | Headlines only - fast preview |
How to Use
-
Formulate your question:
- "What did I decide about database choice?"
- "Error handling conventions"
- "Windows compatibility issues"
-
Run the skill:
- Cortex will search and return relevant memories
-
Follow up:
- If too broad, narrow with more specific terms
- If too specific, broaden the query
Example Queries
async rust framework choice- Architecture decisionerror handling patterns- Coding conventionswindows file path issue- Bugfix lessonauthentication approach- Security decision
Integration
This skill uses the cortex_query MCP tool with your $ARGUMENTS as the need. Prefer cortex_orient once at session start. cortex_recall is a legacy alias.
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.
- 28d ago Changed a877e97f638d
- 1mo ago First seen · 52 lines · 34 tokens per session scan A a25db9f9c23d
recall is a skill published in the GitHub repository AdityaVG13/cortex (8 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 410 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
llm-wiki
Build, ingest, query, and lint a persistent Markdown knowledge base using the Karpathy LLM Wiki pattern. Use for adding sources, maintaining interlinked wiki pages, answering from the knowledge base, filing durable research, or checking contradictions and index health. Do not use it to persist ordinary chat or…
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
memory-management
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
update
Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email.
memoryguard
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
memory-consolidate
Consolidate L1 memory atoms into L2 scene blocks and L3 persona. Invoked by the memory-consolidator agent, or manually via /memory-consolidate.