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-distillgit 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-distill)<a href="https://agentmods.dev/skills/xbluesky/cortexes/cortex-distill"><img src="https://agentmods.dev/badge/skills/xbluesky/cortexes/cortex-distill/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-distill"><img src="https://agentmods.dev/badge/skills/xbluesky/cortexes/cortex-distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 26 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.
- high Anti-Refusal · line 59 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 370 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.05164 |
| Opus 5.5 | $0.00016 | $0.02066 |
| Sonnet 5.5 | $0.00008 | $0.01033 |
| Haiku 4.5 | $0.00004 | $0.00516 |
Grade A, and why
cortex-distill 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Distill — Refine Raw Records
Extract valuable knowledge from Raw/ session dumps into Notes/ and Projects/.
Resolve Vault Path
Read ~/.cortex/config.json to get vault_path.
If the file doesn't exist, tell the user to run /cortexes:genesis first.
Step 1: Find Unprocessed Raw Files
List the distill queue:
cortex-vec distill-queue --root <vault_path>/Raw
This is position-anchored: a Raw counts as distilled only if a
<!-- distilled: ... --> marker appears in its header (before the first
### User turn) or as its last non-empty line. Do NOT grep the
marker string — a pipeline meta-session's body quotes it dozens of times
(it printfs markers onto other files), so grep -rL '<!-- distilled:'
silently drops genuine work from the queue. To check one file, use
cortex-vec raw-state <file>.
Backlog hygiene (only when queue > 1 file)
SessionEnd reclaims the prefix snapshots of the Raw it has just written
(reclaim-superseded --keep <that-file>), but it never looks at an
existing backlog. Before sizing the batch, run the pairwise form once —
no --keep — so strict-prefix duplicates leave the queue:
cortex-vec reclaim-superseded --root <vault_path>/Raw # list only
cortex-vec reclaim-superseded --root <vault_path>/Raw --apply --vault <vault_path>
Applying is safe: a candidate is removed only when it is a line-for-line prefix of a longer queued recording, so no content is lost.
That tool does NOT catch a second class of duplicate: the same transcript
captured twice whose filter output diverged (the residue classifier is
not deterministic — one copy kept a /context table, the other a
Log Summary). Neither copy is a prefix of the other, and the two files
may carry different repo: labels or even different dates. What they
share is raw_bytes in the audit line — the size of the source
transcript — so scan for collisions and treat each group as a triage
hint, never as a deletion list:
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 · +74 lines 32755ab1b976
- 1mo ago Changed 216e078af7f1
- 1mo ago First seen · 407 lines · 41 tokens per session scan A 617df3e7dc8c
cortex-distill is a skill published in the GitHub repository XBlueSky/cortexes (24 stars, last pushed 29d ago), licensed Apache-2.0. It adds 41 tokens to every session and 5,164 once invoked, about $0.0002 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.