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 sbhooley/ainativelang --skill ainlgit clone --depth 1 https://github.com/sbhooley/ainativelangWrote 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/sbhooley/ainativelang/ainl)<a href="https://agentmods.dev/skills/sbhooley/ainativelang/ainl"><img src="https://agentmods.dev/badge/skills/sbhooley/ainativelang/ainl/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/sbhooley/ainativelang/ainl"><img src="https://agentmods.dev/badge/skills/sbhooley/ainativelang/ainl.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 | $0.00021 | $0.01123 |
| Opus 5.5 | $0.00008 | $0.00449 |
| Sonnet 5.5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade D, and why
AINL scanned grade D 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
This skill is designed for environments with **PEP 668 externally-managed Python** (Python 3.13+, sudo blocked). Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/ainl-repo /data/.openclaw/workspace/skills/ainl /data/.local/lib/python3.13/site-packages/*ainl* How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AINL for ZeroClaw
AINL is an AI-native language that compiles deterministic graphs. In ZeroClaw, use it to import workflows, compile them, run them, and expose ainl-mcp tools to the agent.
Package: ainativelang v1.8.0 (this tree; PyPI after publish — docs/RELEASING.md). Optional extras: [mcp], [solana].
Agent instructions
Follow this skill when the user is on ZeroClaw (or wants deterministic .ainl graphs with import / compile / run / MCP). Prefer ./install.sh after zeroclaw skills install …, or the manual pip install 'ainativelang[mcp]' && ainl install-mcp --host zeroclaw path (alias ainl install-zeroclaw). After bootstrap, suggest the morning briefing prompt example below when it fits.
When to use this skill
- The user wants portable, compiled workflows (
.ainl) instead of ad-hoc prompts. - They mention import, compile, morning briefing, clawflows, ecosystem, or deterministic graphs.
- They need MCP access to validation / compile / ecosystem listing (
ainl-mcp).
Install (pick one)
-
From this skill directory (recommended with
zeroclaw skills install): run./install.sh
That upgradesainl[mcp]and runsainl install-mcp --host zeroclaw(pip self-upgrade, MCP registration hints,~/.zeroclaw/bin/ainl-runshim). -
Manual:
pip install 'ainativelang[mcp]' && ainl install-mcp --host zeroclaw
Restricted environments (OpenClaw, Clawbot, webchat sandboxes)
This skill is designed for environments with PEP 668 externally-managed Python (Python 3.13+, sudo blocked).
- Preferred no-root order is:
python -m venvfirst, then--user, then--break-system-packagesas a last resort. - The installer automatically uses compatible fallback modes when default pip fails.
- Clean uninstall (if needed):
pip3 uninstall -y ainl mcp aiohttp langgraph temporalio
rm -rf /tmp/ainl-repo /data/.openclaw/workspace/skills/ainl /data/.local/lib/python3.13/site-packages/*ainl*
What ships with it
2 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.
- 1mo ago First seen · 80 lines · 21 tokens per session scan D 8f22b3107faf
AINL is a skill published in the GitHub repository sbhooley/ainativelang (639 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,123 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.