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 skills/amitvijapur/cortex/cortex-learnnpx skills add amitvijapur/cortex --skill cortex-learngit clone --depth 1 https://github.com/amitvijapur/cortexWhat 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 | $0.00045 | $0.00443 |
| Opus 5 | $0.00023 | $0.00221 |
| Sonnet 5 | $0.00009 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
cortex-learn 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 2d 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-learn
Run pattern detection on ~/.claude/cortex-log.jsonl. Surface groups of routing decisions that repeated ≥3 times as candidate Decision Shortcuts for cortex.md.
When to invoke
- User types
/cortex-learnexplicitly - User asks "what patterns is cortex seeing"
- User asks "are there routes I should codify"
- User says "tune cortex based on usage"
- Session-start check (via
cortex learn --check) surfaced a pending pattern
What to do
Step 1 — Run pattern detection
python3 ~/.claude/bin/cortex learn
Optional:
--threshold N— change minimum count (default 3)--check— terse one-liner for session-start use (no review flow)--no-proposals— skip writing markdown proposal files
Step 2 — Review the proposals
For each detected pattern, the tool writes a markdown proposal file with frontmatter status pending. The user should:
- Read each proposal
- Decide: approve, modify, or reject
- Edit the proposal frontmatter to reflect the decision
- If approved: add the candidate shortcut to
cortex.md→ Decision Shortcuts table - If rejected: write a one-line reason in the Notes section
Step 3 — Update cortex.md (only if approved)
Take the candidate shortcut row and merge it into the Decision Shortcuts table in cortex.md. Don't overwrite existing rows that already cover the same case.
Do NOT
- Do not auto-apply patterns to cortex.md — Amit must approve each one
- Do not delete proposal files even after approval; they're the audit trail
- Do not skip the
--no-proposalsflag if the user explicitly asks for stats only
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.
- 2d ago First seen · 51 lines · 45 tokens per session scan A 7a20b56cd527
cortex-learn is a skill published in the GitHub repository amitvijapur/cortex (5 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 443 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 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…