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 XBlueSky/cortexes --skill cortex-broadcastgit clone --depth 1 https://github.com/XBlueSky/cortexesWrote 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/xbluesky/cortexes/cortex-broadcast)<a href="https://agentmods.dev/skills/xbluesky/cortexes/cortex-broadcast"><img src="https://agentmods.dev/badge/skills/xbluesky/cortexes/cortex-broadcast/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/xbluesky/cortexes/cortex-broadcast"><img src="https://agentmods.dev/badge/skills/xbluesky/cortexes/cortex-broadcast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 42 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00081 | $0.03411 |
| Opus 5.5 | $0.00032 | $0.01364 |
| Sonnet 5.5 | $0.00016 | $0.00682 |
| Haiku 4.5 | $0.00008 | $0.00341 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 359 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 /cortexes:genesis first.
Step 1: Resolve Arguments
The command supports three invocations:
| Form | Action |
|---|---|
/cortexes:broadcast (no args) |
Pop the first (oldest) Raw from the eligible queue |
/cortexes:broadcast <raw-path> |
Use the specified Raw (relative or absolute path) |
/cortexes: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.
- 28d ago Changed · +5 lines 58b2aea97c47
- 1mo ago Changed 89609214596a
- 1mo ago First seen · 354 lines · 81 tokens per session scan A 27ed21559db3
cortex-broadcast is a skill published in the GitHub repository XBlueSky/cortexes (24 stars, last pushed 29d ago), licensed Apache-2.0. It adds 81 tokens to every session and 3,411 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
setup
Set up and verify a first memtomem memory source. Use for onboarding, choosing an index path, or confirming that search works.
status
Check memtomem configuration, storage, index counts, dense coverage, and warnings. Use when search is empty, degraded, or needs diagnosis.
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
garden-tending
Tend the knowledge garden — diagnose vault health, condense project memos into project.md overviews, create/merge cross-project topics, fix broken links, archive superseded notes, extend trails. Trigger on "tend the garden", "condense", "update project overview", "check vault health", "where are we with X?", "what…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.