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 agentmods add skills/dimitrigeelen/agentic-engineering-framework/aef-assistantnpx skills add DimitriGeelen/agentic-engineering-framework --skill aef-assistantgit clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-frameworkWrote 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/dimitrigeelen/agentic-engineering-framework/aef-assistant)<a href="https://agentmods.dev/skills/dimitrigeelen/agentic-engineering-framework/aef-assistant"><img src="https://agentmods.dev/badge/skills/dimitrigeelen/agentic-engineering-framework/aef-assistant.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 | $0.00059 | $0.00636 |
| Opus 5 | $0.00030 | $0.00318 |
| Sonnet 5 | $0.00012 | $0.00127 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade C, and why
aef-assistant scanned grade C with 1 finding 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive commands (`rm -rf`, `git reset --hard`, `git push --force`, `--no-verify`) are gated at Tier 0. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Engineering Framework (AEF) Antigravity Skill
This skill teaches Antigravity / OpenGravity (AGY) agents and subagents how to navigate and operate within an AEF-governed repository.
Core Directives & Invariants
-
P-002: Task-First Structural Enforcement
- No source code or configuration modifications without an active task in
started-workstate. - Run
bin/fw work-on "<task name>" --type buildorbin/fw work-on T-XXXto establish focus. - Every git commit MUST reference a task ID:
git commit -m "T-XXX: <summary>".
- No source code or configuration modifications without an active task in
-
Tier 0 Protection & Human Sovereignty
- Destructive commands (
rm -rf,git reset --hard,git push --force,--no-verify) are gated at Tier 0. - Never attempt to approve your own work. Ask the human operator to run
bin/fw tier0 approveor record decisions.
- Destructive commands (
-
Inceptions & Architecture Exploration
- Use
bin/fw inception start "<name>"for architecture, spikes, or strategic decisions. - Declare open questions (
- **IW-N: <question>**) with confidence ratings (0-3). - Inceptions end in a human decision (
bin/fw inception decide T-XXX go|no-go|defer).
- Use
-
Component Fabric & Dependency Tracking
- View fabric graph:
bin/fw fabric overview - Check architectural drift:
bin/fw fabric drift - Register components:
bin/fw fabric register
- View fabric graph:
-
Subagent Delegation & Concurrency
- When spawning subagents via
invoke_subagent, always pass the current Task ID (T-XXX) in the initial prompt so the subagent operates within the task boundary. - Use branch workspaces for isolated experiments and share workspaces for read-heavy investigations.
- When spawning subagents via
-
TermLink Cross-Terminal & Multi-Agent Mesh
- Check status:
termlink list --json - Interact with workers:
termlink interact <session> "<command>" --json - Send PTY inputs:
termlink pty inject <session> "<prompt>" --enter - Post results to AEF Bus:
bin/fw bus post --task T-XXX --agent antigravity --summary "<summary>"
- Check status:
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.
- today First seen · 48 lines · 59 tokens per session scan C a7d5c4c9753f
aef-assistant is a skill published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 636 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
runtime-admissibility-review
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…
launch-demo
Launch and drive the KB Platform demo locally — bring the Docker Compose stack up, seed the demo data, verify health, and open the web app at http://localhost:3000. Use when asked to run, start, launch, or smoke-check the demo or app.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…