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/xbluesky/cortexes/cortex-evolvenpx skills add XBlueSky/cortexes --skill cortex-evolvegit clone --depth 1 https://github.com/XBlueSky/cortexesWhat 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 | $0.00058 | $0.00953 |
| Opus 5 | $0.00029 | $0.00477 |
| Sonnet 5 | $0.00012 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
cortex-evolve 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Evolve — Save to Vault
Save content to the cortex Obsidian vault.
Resolve Vault Path
Read ~/.cortex/config.json to get vault_path.
If the file doesn't exist, tell the user to run /cortex:genesis first.
All file paths below are relative to the vault root.
Determine Content Type
Ask the user if unclear. Use these heuristics:
| Signal | Type | Target |
|---|---|---|
| Technical knowledge, how-to, concept explanation | Notes | Notes/<category>/<title>.md |
| Related to a specific repo's design, decision, or progress | Projects | Projects/<repo-name>/<title>.md |
Writing to Notes
- Determine category from content (C++, Linux, Nginx, Web, or create new)
- Create file at
Notes/<category>/<title>.md - Use this template:
---
title: <title>
tags:
- <relevant-tags>
created: <YYYY-MM-DD>
source: cortex
---
# <title>
<content>
<optional: related wikilinks like [[nginx-cert-renew]] or [[other-note]]>
- Use Obsidian wikilinks
[[note-name]]for vault-internal references - Use standard markdown links
[text](url)for external URLs only
Writing to Projects
- Determine repo name (from current session context or ask user)
- If
Projects/<repo-name>/_index.mddoesn't exist, create it:
---
title: <repo-name>
repo: <git-remote-url>
tags:
- project
---
# <repo-name>
<brief description>
- Create topic file at
Projects/<repo-name>/<topic>.md
Update _index.md
After writing the file:
-
Read
<vault_path>/_index.md -
Append a row under the matching
###sub-section, creating the sub-section (with its table header) if it does not exist yet:- Notes →
### <topic>under## Notes:| [[title]] | tags | one-line summary | - Projects →
### <repo-name>under## Projects:| [[topic-title]] | tags | summary |
Rows are per-page, not per-repo: a new repo means a new
###sub-section, not a single row standing for the whole repo. - Notes →
-
Bump the
updateddate in frontmatter. There is noentries:count to maintain — the field was removed by design (see/cortex:genesis).
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 · 128 lines · 58 tokens per session scan A 788a4a901324
cortex-evolve is a skill published in the GitHub repository XBlueSky/cortexes (20 stars, last pushed 26d ago), licensed Apache-2.0. It adds 58 tokens to every session and 953 once invoked, about $0.0003 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 skills, from other repositories
vera
Code search over the current repository. Before reading files to answer "where is X", "how does Y work", "find Z", or "what calls W", run vera search " " or vera references first. Use vera grep for exact strings and regex, vera structural for definitions, routes, and env reads. Do not read multiple files hoping to…
semantic-search
Code search for this repo — pick the right Beacon tool for the question: exact symbol lookup, reference tracing, file outline, or semantic search.
release-gatekeeper
End-to-end release validation for Connapse — the 'final boss' before any version ships. Downloads the latest alpha from GitHub Releases, deploys an isolated Docker instance (separate from production), then systematically tests every feature: UI via Playwright, API via curl/REST, MCP tools, search quality, security…
create-tickets
Batch-create GitHub issues from a brainstorming discussion. Decomposes ideas into properly-sized tickets with labels, milestones, and project board placement. Trigger when user says: create tickets, make tickets, turn ideas into issues, create issues from brainstorm, create issues from discussion, batch create issues.
discover-work
Deep research across codebase, GitHub issues, discussions, project board, and architecture docs to discover new tasks, gaps, technical debt, and improvement ideas. Trigger when user says: discover work, find tasks, what needs doing, audit codebase, find gaps, technical debt audit, backlog discovery, brainstorm tasks…
next-task
Recommend the best next task to work on based on open GitHub issues. Analyzes priority, dependencies, milestone urgency, and codebase readiness. Trigger when user asks: what should I work on, what is next, next task, pick a task, what to do next, suggest work, prioritize tasks.