Borrowing it
Nothing to install: this file belongs to lktiep/cortex-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lktiep/cortex-hub/master/.claude/commands/cs.mdgit clone --depth 1 https://github.com/lktiep/cortex-hubWrote 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/commands/lktiep/cortex-hub/cs)<a href="https://agentmods.dev/commands/lktiep/cortex-hub/cs"><img src="https://agentmods.dev/badge/commands/lktiep/cortex-hub/cs/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/commands/lktiep/cortex-hub/cs"><img src="https://agentmods.dev/badge/commands/lktiep/cortex-hub/cs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00533 |
| Opus 5.5 | $0.00000 | $0.00213 |
| Sonnet 5.5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
cs 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 today.
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
/cs — Cortex Start v0.10.0
Version: 0.10.0 | Updated: 2026-10-22 Changelog: v0.10.0 — one call: session_start with the task answers the recall and the files to read Changelog: v0.9.4 — recall with the task's own words; the generic session query is already in session_start's answer Changelog: v0.9.0 — cortex_plan_quality is actually registered; it scores 0-10 and takes the request too Changelog: v0.8.0 — search-once/read-all-ten ordering from measured retrieval; recall no longer counts as discovery
1. Start, with the task
cortex_session_start(repo: "https://github.com/lktiep/cortex-hub.git", task: "<the task in a few words>")
The task's own words: the feature, the error, the file. The answer holds the recall for it
(recalled: knowledge and memory) and where the code is (located: files, line ranges, symbols).
That is the recall and the first lookup: do not repeat them with separate searches. A hook adds
the conversation id, branch, IDE and identity. No task yet? Start without one, and call it again
with the task once you have it.
2. Only when it applies
- Uncommitted changes in
git status→cortex_detect_changes(diff: "<git diff HEAD>"). - Shared files another agent may hold →
cortex_changes(projectId). - Conductor work →
cortex_task_pickup(); thencortex_task_accept,cortex_task_update. - A plan of several steps →
cortex_plan_quality(plan, request); 8.0 or more → execute.
3. While working
- A symbol name →
cortex_code_context(name). A behaviour →cortex_code_search(query). An exact literal →rg; in the organization's other repos →cortex_code_grep. Read the lines a hit names, not the whole file. - Something breaks →
cortex_knowledge_searchandcortex_memory_searchwith the error; a non-obvious fix →cortex_knowledge_store. - Before committing → build, typecheck and lint last, then
cortex_detect_changes(diff); after pushing →cortex_code_reindex(repo, branch).
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.
- today Changed · -85 lines 70c4d9df3410
- yesterday Changed · -2 lines 05333cf177fa
- 13d ago Changed · +4 lines ca89a376c3ed
- 24d ago Changed · +20 lines 8fb707638f2e
- 1mo ago First seen · 95 lines · 0 tokens per session scan A 4bc850db1ff1
cs is a command published in the GitHub repository lktiep/cortex-hub (93 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 533 tokens. 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 commands, from other repositories
context-save
Save project context, decisions, and progress for a later session.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.