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 Chemaclass/agnostic-ai --skill importgit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/import)<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/import"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/import.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00617 |
| Opus 5 | $0.00030 | $0.00309 |
| Sonnet 5 | $0.00012 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
import 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 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.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
import
Captures what one tool already knows and makes it drive all of them, without retyping the conventions.
Steps
-
Confirm the CLI is present:
agnostic-ai --version. If missing, run theinstallskill first. -
Inventory what exists. Check for
CLAUDE.md,AGENTS.md,GEMINI.md,CONVENTIONS.md,.cursor/rules/,.cline/rules/,.devin/rules/,.continue/rules/,.github/copilot-instructions.md, and any.claude/{agents,skills,settings.json}. -
Scaffold the config if absent:
agnostic-ai init. -
Import each source you found, one command per tool:
agnostic-ai import claude # CLAUDE.md + .claude/{agents,skills,settings.json} agnostic-ai import codex # AGENTS.md, root and nested agnostic-ai import cursor # .cursor/rules/*.mdc agnostic-ai import cline # .cline/rules/, .cline/agents/ agnostic-ai import windsurf # .devin/rules/ agnostic-ai import continue # .continue/rules/importwrites spec files only. It never editstargets:or the rest of the config. -
Commit the import before syncing, then sync as its own commit:
git add .agnostic-ai/ agnostic-ai.yaml git commit -m "chore(agnostic-ai): import existing config" agnostic-ai sync git add -A git commit -m "chore(agnostic-ai): regenerate per-target configs"Splitting them keeps the review honest: the first commit carries the real content, the second is mechanical (headers, key order) and can be skimmed.
-
Read the imported specs with the user. An imported rule often mixes several concerns because it came from one long file; split it into one file per rule so scoping and per-target emission work properly.
Notes
- Importing from several tools: run each
importand its commit before the finalsync. - Round-trip is byte-stable:
importstrips the generated markers it wrote, so a latersyncproduces the same bytes. - What
importdoes not capture: helper scripts referenced fromsettings.json,statusline.sh, and ad-hoc config files. Keep those in git next to.agnostic-ai/. Files bundled inside a skill directory do round-trip.
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 · 45 lines · 59 tokens per session scan A 6cd02834edb3
import is a skill published in the GitHub repository Chemaclass/agnostic-ai (11 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 617 once invoked, about $0.0003 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
cdaf
Read CDAF sidecar files (.cdaf) instead of processing video with vision. Use whenever a task involves understanding, summarizing, searching, editing, or selecting from video files (b-roll, raw clips, footage libraries) — check for a .cdaf sidecar FIRST before analyzing any video directly.
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
pptx
Read, create, and convert Microsoft PowerPoint (.pptx) presentations — extract slide text to JSON/markdown, build decks from JSON/markdown outlines, and export to PDF.
xlsx
Read, create, and convert Microsoft Excel (.xlsx) and CSV spreadsheets — extract sheets and tables to JSON, build workbooks from JSON/CSV, and export to PDF.
Read and create PDF documents — extract text (and per-page text) from a PDF to JSON/markdown, and render markdown/plain text into a new PDF.
duduclaw-platform
Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (npx duduclaw onboard…