Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CrowdStrike/foundry-skillsnpx agentmods add skills/crowdstrike/foundry-skills/ai-agents-developmentWrote 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/crowdstrike/foundry-skills/ai-agents-development)<a href="https://agentmods.dev/skills/crowdstrike/foundry-skills/ai-agents-development"><img src="https://agentmods.dev/badge/skills/crowdstrike/foundry-skills/ai-agents-development/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/crowdstrike/foundry-skills/ai-agents-development"><img src="https://agentmods.dev/badge/skills/crowdstrike/foundry-skills/ai-agents-development.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 | $0.00220 | $0.05234 |
| Opus 5.5 | $0.00088 | $0.02094 |
| Sonnet 5.5 | $0.00044 | $0.01047 |
| Haiku 4.5 | $0.00022 | $0.00523 |
Grade A, and why
ai-agents-development 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 yesterday.
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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry AI Agents and Knowledge Bases
Create knowledge bases before the agents that reference them, and scaffold both with the CLI.
Part of a suite. If
development-workflowhas not already run, and this is a new app or its first capability, load thedevelopment-workflowskill first — it owns the CLI prerequisite check, scaffolding order, and manifest coordination.
An AI agent is a Foundry artifact that pairs a system prompt with a model, a set of tools, and optional knowledge bases. A knowledge base is a named bundle of files the agent can draw on. Both live under a single ai: block in manifest.yml.
Agents are the only consumer of knowledge bases. A knowledge base on its own does nothing; a collection or API integration becomes agent-usable only when it is exposed as a tool and named in the agent's tools list.
Build Order Is Mandatory
1. Collections / API integrations (if the agent needs them as tools)
2. Knowledge bases → foundry knowledge-bases create
3. Agents → foundry agents create (exposure via --expose-* flags)
4. Hand-edit ai.agents[].model / .tools (no CLI flags exist for these two)
Create knowledge bases first. foundry agents create --knowledge-bases X validates that X is already in the manifest and fails the whole command otherwise:
agent "my_agent" references knowledge base "X" which is not defined in the manifest
The agent directory is rolled back, so nothing is left half-created.
Naming and Description Constraints
Both artifacts share the CLI's create-time validators, which bite constantly: names are 5–100 chars (must start alphanumeric; kb, agent, bot all fail), descriptions 3–500 chars when present (-d "x" fails), agent names unique among agents and KB names among KBs. KBs are the one asymmetry — knowledge-bases create enforces the 5-char floor, but the manifest validator accepts a KB name as short as 1 character (and no longer checks the description), so a short name already in the manifest passes apps validate. The on-disk directory is a sanitized form of the name (every char outside [a-zA-Z0-9-_] → _, then leading/trailing _ trimmed): --name "Threat Intel Docs" yields knowledge-bases/Threat_Intel_Docs/ and records path: Threat_Intel_Docs; the manifest resolves files against path, never name. Full regex/length table: references/manifest-schema.md.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 9f54a10c7698
- 2d ago Changed · -88 lines 3c7645220b1d
- 8d ago Changed · -2 lines e2636bb1c3f9
- 15d ago Changed 06647c378267
- 23d ago Changed · +2 lines 372be4fa8855
- 28d ago Changed 60e1e06518b8
- 29d ago Changed · +6 lines 35ac04c4520a
- 1mo ago Changed · -4 lines cbf8885f7588
- 1mo ago Changed · +20 lines bdd7b8a450cb
- 1mo ago First seen · 297 lines · 220 tokens per session scan A 3b4ddec24367
ai-agents-development is a skill published in the GitHub repository CrowdStrike/foundry-skills (35 stars, last pushed today), licensed MIT. It adds 220 tokens to every session and 5,234 once invoked, about $0.0009 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 2026-09-22.
Other skills, from other repositories
foundry-redirect
TRIGGER when the user asks to "build a Foundry app", "create a Foundry app", mentions manifest.yml, or needs a UI page/extension, serverless function, collection, or a custom API integration from a third-party API (Okta, ServiceNow, Jira, etc.) built. DO NOT TRIGGER for a standalone Fusion workflow that only wires…
notify-user
Telegram comms playbook for Antigravity — when and how to reply, ack long work, present choices, and delegate to other agents. Use whenever you're paired to a Telegram chat via the telegram-agy MCP server and need to talk back to the user. The chat is your only signal channel — terminal output never reaches the user.
use-browser
Do something on a website in a real browser on the box — click, type, fill a form, search, check a page, add to a cart, star a repo, draft a reply. Use for "go to and …", "buy/book/fill/submit/check … on ", "open and …", or anything a normal fetch cannot do (JavaScript pages, clicks, forms, logged-in pages). Works…
connect-site
Get a human logged into a site on the box, then use that logged-in session. Use when you need a site the agent has no session for — "log in to X", "connect my X account", "the agent needs a logged-in X", "open a browser on the box", "X says I'm signed out" — or when 5dive browser status is not authenticated. Not for…
ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.