Borrowing it
Nothing to install: this file belongs to agno-agi/agentos-modal. 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/agno-agi/agentos-modal/main/.agents/skills/extend-agent/SKILL.mdgit clone --depth 1 https://github.com/agno-agi/agentos-modalWrote 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/agno-agi/agentos-modal/extend-agent)<a href="https://agentmods.dev/skills/agno-agi/agentos-modal/extend-agent"><img src="https://agentmods.dev/badge/skills/agno-agi/agentos-modal/extend-agent.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 5.1 | $0.00114 | $0.02128 |
| Opus 5 | $0.00057 | $0.01064 |
| Sonnet 5 | $0.00023 | $0.00426 |
| Haiku 4.5 | $0.00011 | $0.00213 |
Grade B, and why
extend-agent scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- `curl -sSf http://localhost:8000/health` returns 200 (else ask for `docker compose up -d --build`). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -sSf http://localhost:8000/health` returns 200 (else ask for `docker compose up -d --build`). This is a copy
100% identical to extend-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extend an Agent
Coding-agent workflow: run as
/extend-agentor by describing the task.
The user names a change; you implement it, verify it against the live agent, and ask if there's more. Stop when they say done. The autonomous half is improve-agent — run it afterward.
The platform is on http://localhost:8000 (RUNTIME_ENV=dev); code edits hot-reload.
0. Preconditions
curl -sSf http://localhost:8000/healthreturns 200 (else ask fordocker compose up -d --build).- The container is bound to this checkout:
docker inspect agentos-api --format '{{range .Mounts}}{{.Source}}{{"\n"}}{{end}}' | grep -F "$(pwd)"prints a line. Empty →cdto the bound repo or restart compose from here. - Ask for the target slug. Suggest a branch:
git checkout -b extend/<slug>-$(date +%Y%m%d).
1. Read the agent
Confirm the slug is code, not a Studio-built component:
curl -s http://localhost:8000/agents | jq -r '.[] | "\(.id)\tis_component=\(.is_component)"'
is_component=true has no source file — route the change through Platform Builder (edit_agent / edit_team / edit_workflow, then publish_component). Never create agents/<slug>.py under that id: code wins on resolution and silently shadows the built component.
Open the file — agents/<slug>.py, or for the reference components platform-builder → agents/builder.py, platform-manager → agents/manager.py, platform-engineer → agents/engineer.py, agno → teams/lead.py. Capture purpose (docstring + INSTRUCTIONS), tools, pattern, and the existing levers (learning=, knowledge=, num_history_runs, model). Restate the purpose in 1–2 sentences.
2. Ask what to change
Structured choice when the harness has one, else plain text. Multi-select is fine — handle sequentially, then loop:
- Add a tool — MCP server, agno toolkit, or function tool.
- Add a capability — knowledge base, learning/memory, sub-agent/context provider, scheduled task.
- Grow the registry — declare a block in
app/registry.pyso everything the platform builds can carry it. Offer this unprompted when the ask is plural ("agents should be able to…"). - Refine instructions — clarify, narrow, change tone or format.
- Fix a bug — ask for the failing prompt, the observed behavior, what they want instead.
- Something else.
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.
- 7d ago First seen · 113 lines · 114 tokens per session scan B 149dbec12b67
extend-agent is a skill published in the GitHub repository agno-agi/agentos-modal (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 114 tokens to every session and 2,128 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 100% identical to extend-agent, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
protein-binder-design
Design and validate de novo protein binders with the current NVIDIA BioNeMo Agent Toolkit workflow, while adapting honestly when NVIDIA-hosted credentials are unavailable.
interaction-patterns
UI interaction design patterns for skeleton loading, infinite scroll with accessibility, progressive disclosure, modal/drawer/inline selection, drag-and-drop with keyboard alternatives, tab overflow handling, and toast notification positioning. Use when implementing loading states, content pagination, disclosure…
agentos-ui-ux
Design, review, or implement AgentOS UI and UX work using the project’s operator-console visual system. Use for React/Tailwind pages, cards, dialogs, mobile layouts, theme work, navigation, forms, empty/loading/error states, and UI consistency reviews in AgentOS.
modal
Use when running Python or GPU workloads serverlessly on Modal — modal.App, inline container Images, gpu= on @app.function, Volumes for weight caching, Cron schedules, ASGI endpoints, modal run vs serve vs deploy. NOT managed prediction APIs with no container of your own (that is replicate); NOT SSH-able GPU boxes…
swiftui-backports
Find SwiftUIBackports replacements for SwiftUI APIs unavailable on a project deployment target. Use for Swift/SwiftUI compiler availability errors, old iOS/tvOS/watchOS/macOS targets, or when implementing SwiftUI app features that may benefit from SwiftUIBackports.