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 AgiFlow/aicode-toolkit --skill create-projectgit clone --depth 1 https://github.com/AgiFlow/aicode-toolkitWrote 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/agiflow/aicode-toolkit/create-project)<a href="https://agentmods.dev/skills/agiflow/aicode-toolkit/create-project"><img src="https://agentmods.dev/badge/skills/agiflow/aicode-toolkit/create-project/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/agiflow/aicode-toolkit/create-project"><img src="https://agentmods.dev/badge/skills/agiflow/aicode-toolkit/create-project.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 | $0.00038 | $0.00196 |
| Opus 5.5 | $0.00015 | $0.00078 |
| Sonnet 5.5 | $0.00008 | $0.00039 |
| Haiku 4.5 | $0.00004 | $0.00020 |
Grade A, and why
create-project 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 18d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 18d ago First seen · 12 lines · 38 tokens per session scan A 13ac88a22fa2
create-project is a skill published in the GitHub repository AgiFlow/aicode-toolkit (161 stars, last pushed 4d ago), licensed AGPL-3.0. It adds 38 tokens to every session and 196 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 2026-09-28.
Other skills, from other repositories
obto-build-loop
This skill should be used when the user asks to "build an app on OBTO", "create an OBTO app", "scaffold an app", "add a page/route/script to my OBTO app", or any task that creates or modifies OBTO application artifacts. Covers the stateless contract, the reliability-first build loop, and the done-means-done smoke gate.
obto-troubleshooting
This skill should be used when the user reports an OBTO error, asks "why did this OBTO call fail", mentions errors like collectionnotinallowlist, must pass appName/domain, hostmismatch, scopeownershipmismatch, stale tools, or wants to debug an OBTO app via logs. Covers the structured error envelope and the standard…
obto-deploy
This skill should be used when the user asks to "deploy to OBTO", "upload a large file/module to OBTO", "ship this artifact", "push this script to the platform", or when any single artifact source is too large for one tool call. Covers deployment order, choosing the write path (patch vs. upsert vs. chunked vs.…
obto-developer
Build and deploy full-stack apps on the OBTO platform via MCP tools. OBTO stores all code as MongoDB records — no filesystem. Covers the stateless contract (appName + domain on every call), the collections (pltfpage, pltfjavascript, pltfstylesheet, pltfuitemplate, pltfscriptclient, pltfpolicyclient, pltfscriptserver…
obto-platform-boundary
This skill should be used whenever work on OBTO stalls on something that looks like infrastructure — code that was saved but is not live, a host or URL that serves the wrong thing, a route that 404s after being created, DNS or certificate questions, a tool that refuses with a capability or activation error, or any…
obto-upload
This skill should be used when the user asks to upload a LOCAL binary/media file (image, video, PDF, or other asset) into OBTO and get back a served/CDN URL — "upload this image to OBTO", "host this file on OBTO", "get a served URL for this asset", "obtorequestuploadurl", "obtouploadmedia", "obtostagechunk". Covers…