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 amitvijapur/cortex --skill cortex-initgit clone --depth 1 https://github.com/amitvijapur/cortexWrote 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/amitvijapur/cortex/cortex-init)<a href="https://agentmods.dev/skills/amitvijapur/cortex/cortex-init"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-init/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/amitvijapur/cortex/cortex-init"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-init.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 | $0.00061 | $0.01025 |
| Opus 5.5 | $0.00024 | $0.00410 |
| Sonnet 5.5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
cortex-init 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cortex-init — adopt the user's existing stack into Cortex
Cortex is a routing layer. This skill wires it around whatever the user already runs, instead of imposing a fixed toolset. Their systems are preserved and tied together — nothing is replaced, and their cortex.md is never overwritten without a backup and their confirmation.
Run these steps in order.
1. Discover — deterministic scan
Resolve paths once and use these same values throughout setup. State precedence is
CORTEX_HOME, then CLAUDE_DIR, then $HOME/.claude, matching the CLI and installer.
Keep a custom override exported in the agent's environment for later skill calls.
The executable is installed under that state directory. Keep paths quoted so custom
directories containing spaces work. Run the scanner:
cortex_state_dir="${CORTEX_HOME:-${CLAUDE_DIR:-$HOME/.claude}}"
cortex_executable="$cortex_state_dir/bin/cortex"
python3 "$cortex_executable" init
It writes <state-dir>/cortex-inventory.json and prints a summary. Read the JSON. It lists their agents (counted by division), skills, commands, MCP servers, hooks, plugins, detected other-agent config files (Cursor / Codex / Gemini / Aider / Windsurf), and relevant CLIs on PATH.
2. Interview — fill gaps, don't interrogate
Auto-accept the obvious; only ask what you genuinely cannot infer. Keep it to a handful of questions. Ask about:
- Grouping: large pools (e.g. "262 agents across 21 divisions") — one "Specialist Agents" pool, or break out a few they reach for often?
- Category for any MCP/tool you can't classify from its name (search? database? scraping? design? docs?).
- Defaults per task class — for
build,review,plan,research,debug,design, which of their systems is the go-to? Offer a sensible guess and let them correct it. - Exclusions — anything detected that they do not want Cortex to route to.
Use their answers, not assumptions.
3. Synthesize the registry
Write a Workflow Registry in the exact shape Cortex uses (mirror the ## Workflow Registry section of the installed cortex.md). For each system / agent-group / skill-family / MCP:
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.
- 6d ago Changed · +1 lines 85292495bfcb
- 1mo ago Changed · +8 lines bb14a792190e
- 1mo ago First seen · 70 lines · 61 tokens per session scan A e348b84c6975
cortex-init is a skill published in the GitHub repository amitvijapur/cortex (5 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,025 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 2026-08-31.
Other skills, from other repositories
accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
cuopt-routing-api-python
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
mcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
holoscan-module-lifecycle
Develop external Holoscan Modules with the Holoscan CLI and use them in Holoscan applications: scaffold, test, Python bindings, DEB/WHEEL packaging, and clean-consumer proof.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.