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-delegategit 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-delegate)<a href="https://agentmods.dev/skills/amitvijapur/cortex/cortex-delegate"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-delegate/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-delegate"><img src="https://agentmods.dev/badge/skills/amitvijapur/cortex/cortex-delegate.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 | $0.00041 | $0.01393 |
| Opus 5.5 | $0.00016 | $0.00557 |
| Sonnet 5.5 | $0.00008 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
cortex-delegate 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex delegate
Keep decomposition, review, and synthesis in the parent. Calibrate effort to risk and verification needs, independently of host or model brand. Read the current session's tool contract before dispatch; it takes precedence over examples here.
This skill creates visible, user-owned tasks. It is not an invisible subagent mechanism. Only create one when the user explicitly asks for a new or separate task. Phrases such as create a new task, spin this into a separate task, or start a Work task qualify. Delegate this or use a subagent alone does not qualify unless the surrounding request clearly identifies a separate Codex or Work task. Use the runtime's subagent tools for ordinary bounded subtasks. If the user's intended surface is genuinely ambiguous and changes the outcome, ask one concise question before creating anything.
Choose the lane
| Work needs | Lane |
|---|---|
| Local repository, terminal, tests, or a diff | Codex project task |
| Explicitly requested worktree in a Git repository | Codex worktree task |
| Explicitly requested cloud work task | ChatGPT Work |
| Local files that are not already available to ChatGPT Work | Codex local task, or ask the user to attach the files to Work |
Do not send coding work to ChatGPT Work merely because it is cloud-hosted. Do not send connected-app research to a local worktree merely because the parent is in Codex.
Parent contract
The parent keeps the judgment:
- Decompose the request into independent tasks with explicit acceptance criteria.
- Dispatch only tasks that can succeed with the context available in their lane.
- Inspect the returned output and evidence. Do not forward a child task's conclusion unreviewed.
- Send concrete revision requests only with human authorization to message that task.
- Integrate the results and make the final call in the parent.
Keep delegation bounded. Default to one task. Use parallel tasks only when the work is genuinely independent, and keep the number small enough that the parent can review every result.
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 · -20 tokens per session d951a1971539
- 1mo ago First seen · 84 lines · 61 tokens per session scan A 10051d40b645
cortex-delegate is a skill published in the GitHub repository amitvijapur/cortex (5 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,393 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 2026-09-06.
Other skills, from other repositories
changes-report
Report all repository changes that entered a target branch during one required date or period, grouped by product change and written as plain English for a broad audience. Use for daily, weekly, date-range, or relative-period change summaries rather than explaining one known diff.
coderabbit-triage
Triage unresolved CodeRabbit feedback on the current GitHub pull request. Use for read-only disposition and, only when separately authorized, scoped remediation and remote thread closure.
roadmap-task-deliver
Deliver the first eligible unfinished roadmap task through implementation, review, green CI, PR merge, and a task-status update. Use for autonomous delivery from local roadmap and task files. Files can be outside the code repository or outside Git.
jira-issue-deliver
Autonomously deliver one Jira issue from intake to a ready GitHub pull request. Use only when the user authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback.
plan-deliver
Autonomously deliver an approved implementation plan to a ready GitHub pull request. Use when the user supplies a plan in the conversation or a file and authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback; use jira-issue-deliver when the…
pr-draft
Publish confirmed local changes as a monitored GitHub draft pull request. Use only when the user authorizes branch creation, scoped staging, commit, push, draft PR creation, and CI follow-up.