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-broadcastnpx skills add XBlueSky/cortexes --skill cortex-broadcastgit 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 | $0.00081 | $0.03351 |
| Opus 5 | $0.00041 | $0.01675 |
| Sonnet 5 | $0.00016 | $0.00670 |
| Haiku 4.5 | $0.00008 | $0.00335 |
Grade A, and why
cortex-broadcast 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 3d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Broadcast — Compounding Ingest
Propagate insights from a distilled Raw into related existing Notes/Projects pages through conversational per-page edits.
Resolve Vault Path and Config
Read ~/.cortex/config.json:
jq -r '.vault_path' ~/.cortex/config.json
jq -r '.broadcast.target_top_n // 5' ~/.cortex/config.json
jq -r '.broadcast.target_min_score // 0.40' ~/.cortex/config.json
If the config file doesn't exist, tell the user to run /cortex:genesis first.
Step 1: Resolve Arguments
The command supports three invocations:
| Form | Action |
|---|---|
/cortex:broadcast (no args) |
Pop the first (oldest) Raw from the eligible queue |
/cortex:broadcast <raw-path> |
Use the specified Raw (relative or absolute path) |
/cortex:broadcast --list |
Print the eligible queue and exit |
Step 2: Build Eligible Queue
A Raw is eligible iff its marker meets all of:
- Contains
<!-- distilled: YYYY-MM-DD → ... -->(Phase 1 processed). - Outcome is
neworpending-merge(the marker content after→is either a path likeNotes/X.md/Projects/Y/Z.md, or starts withpending-merge:; anything else —(skip: routine),(no insight), or the pre-Phase-1 legacy(no extractable content)— is ineligible). - Does not already contain any of:
| broadcast:,| merged:,| no-broadcast:.
Build the list via:
cortex-vec broadcast-queue --root <vault>/Raw
This applies the three criteria above against each Raw's authoritative marker
(header marker, or last non-empty line) and returns the result FIFO by path.
Do NOT grep the marker string — a meta-session's body quotes it many
times, which fools a substring scan. To inspect one file, use
cortex-vec raw-state <file>.
Step 3: Handle --list
If the user invoked --list, print each queued Raw with:
- Relative path from vault
- Outcome (extract from marker:
newif target is a path;pending-mergeif marker containspending-merge:) - Original target (for
pending-mergeRaws;—fornew)
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.
- 3d ago First seen · 354 lines · 81 tokens per session scan A 27ed21559db3
cortex-broadcast is a skill published in the GitHub repository XBlueSky/cortexes (20 stars, last pushed 28d ago), licensed Apache-2.0. It adds 81 tokens to every session and 3,351 once invoked, about $0.0004 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.