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 commands/dimitrigeelen/agentic-engineering-framework/exploregit 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/commands/dimitrigeelen/agentic-engineering-framework/explore)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/explore"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/explore.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 | $0.00000 | $0.00368 |
| Opus 5 | $0.00000 | $0.00184 |
| Sonnet 5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
explore 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 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.
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.
What it actually says
/explore - Structured Exploration Before Building
Lightweight exploration to understand a problem before committing to a solution. Use when starting inception tasks, investigating unknowns, or evaluating approaches.
Prerequisites
- Verify an active task exists (
cat .context/working/focus.yaml) - If no task:
fw work-on "description" --type inceptionfirst
Workflow
Step 1: Frame the Problem
State the problem or question in one sentence. Print it clearly.
Step 2: Identify Key Questions
List 3-5 questions that need answers before you can proceed. Number them. Present to user: "These are the questions I need to answer. Anything to add or change?"
Wait for user response before proceeding.
Step 3: Research Each Question
For each question:
- Research it (codebase search, web search, doc lookup — whatever fits)
- Write a one-paragraph finding with source references
Keep research concise. Target: 5-10 minutes total, not 60.
Step 4: Present Options
Based on findings, present numbered options for how to proceed. Include trade-offs for each option (1-2 sentences).
Wait for user to choose before doing anything else.
Rules
- This skill does ONE thing: explore. It does not chain to planning or building.
- No artifacts are written to disk — findings stay in conversation.
- No commits during exploration — this is research, not work.
- If exploration reveals the problem is bigger than expected, say so and suggest task decomposition.
- Target total time: 5-10 minutes. If you're going longer, you're over-exploring.
- Present findings as numbered lists, not prose walls.
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 · 43 lines · 0 tokens per session scan A 82a85a8b9385
explore is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 368 tokens. 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 2026-09-04.
Other commands, from other repositories
service-check
Request each agent to run a self-diagnostic to validate their runtime setup.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
request-research
Ask the researcher to investigate a specific topic.
health
Perform a health check on all agents and identify any issues.
schedules
Quick overview of all schedules across the platform.
status
Report on recent research activity and findings count.