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-takeoffnpx skills add XBlueSky/cortexes --skill cortex-takeoffgit 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-takeoff)<a href="https://agentmods.dev/skills/xbluesky/cortexes/cortex-takeoff"><img src="https://agentmods.dev/badge/skills/xbluesky/cortexes/cortex-takeoff.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01881 |
| Opus 5 | $0.00065 | $0.00941 |
| Sonnet 5 | $0.00026 | $0.00376 |
| Haiku 4.5 | $0.00013 | $0.00188 |
Grade A, and why
cortex-takeoff 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Takeoff — Session Hand-off Baton
A baton is a curated continuation note for ONE work line (topic) in ONE repo.
It lives at <vault>/.takeoff/<repo-slug>/<topic>.md, is git-ignored, and is
consumed by a later session. A repo may hold several batons at once — one per
work line. Batons are independent of the Raw session dump (which SessionEnd
writes automatically). Do NOT commit them, distill them, broadcast them, index
them with cortex-vec, or log them to log.md.
Legacy layout: <vault>/.takeoff/<repo-slug>.md (single-baton era, no topic
key). Legacy batons still list, resume, and clear (via --legacy), and are
retired to the new layout on their next hand-off. Never create new ones.
Locating takeoff.sh
The repo slug and git-safety are handled by takeoff.sh, bundled in this plugin
at hooks/scripts/takeoff.sh. In every mode below, FIRST set TK to that helper,
resolved relative to THIS skill's base directory. The skill-load message announces
the base directory as <...>/cortex/<version>/skills/cortex-takeoff; takeoff.sh
sits two levels up. Substitute the actual announced base-dir path:
TK="<skill-base-dir>/../../hooks/scripts/takeoff.sh"
test -f "$TK" || { echo "cortex: takeoff.sh not found at $TK" >&2; exit 1; }
Do NOT use claude plugin root (no such subcommand) or $CLAUDE_PLUGIN_ROOT
(unset for skill-run bash).
Resolving the repo root
Every bash "$TK" … call takes an EXPLICIT cwd argument — there is no $PWD
fallback (a drifted shell cwd once deleted the wrong repo's baton). Resolve
the repo root ONCE per mode and reuse it verbatim in every call:
cwd="$(git rev-parse --show-toplevel)"
If your shell may have cd'ed to another repo earlier in the session, resolve from a path you KNOW belongs to this repo (e.g. a file you have been editing) instead of trusting the shell's current directory.
Mode
Determined by the command argument:
| Argument | Mode |
|---|---|
(none) or <topic> |
create — write/overwrite one work line's baton |
resume [topic] |
resume — load a baton (do not delete) |
done [topic] |
done — clear a baton (soft-delete to trash) |
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 · 172 lines · 130 tokens per session scan A 82958310bab9
cortex-takeoff is a skill published in the GitHub repository XBlueSky/cortexes (20 stars, last pushed 28d ago), licensed Apache-2.0. It adds 130 tokens to every session and 1,881 once invoked, about $0.0006 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.