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/richfrem/agent-plugins-skills/using-exploration-cyclenpx skills add richfrem/agent-plugins-skills --skill using-exploration-cyclegit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/using-exploration-cycle)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/using-exploration-cycle"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/using-exploration-cycle.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 | $0.00023 | $0.00522 |
| Opus 5 | $0.00012 | $0.00261 |
| Sonnet 5 | $0.00005 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
using-exploration-cycle 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 2d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before responding to ANY user message (including answering general questions or scoping requests), you MUST verify the state of the active exploration session. If a session is in progress, you DO NOT have a choice: you MUST route execution through the active phase of the exploration-workflow.
How to Check Session State
Before generating any response:
- Check if
exploration/exploration-dashboard.mdexists. - If it DOES exist:
- Read the dashboard using the Read tool.
- Check the
**Status:**field. - If status is
Complete, the prior session has ended. You may answer normally or offer to start a new exploration. - If status is
In ProgressorTBD, identify the**Current Phase:**. - Immediately yield control to the active phase of the exploration workflow. Always invoke the
exploration-workflowskill. Never directly invoke child skills unless authorized by the orchestrator. Do NOT answer the user's question directly in freeform prose.
- If it DOES NOT exist:
- If the user's message matches any exploration triggers (e.g. "I want to build...", "Let's explore...", "I have an idea...", "start discovery"), you must bootstrap the session.
- Invoke the
exploration-workflowskill to initiate Phase 0 intake.
State Authority
The SQLite state database and programmatic phase artifacts are the absolute state authority. The markdown dashboard is a read-only projection of the database. Do not rely on conversational chat history to assume a phase is complete or that a gate has been passed.
Active Verification & Review during Waits
When executing the workflow or waiting for sub-agent execution / task completions:
- Proactively read and review the artifacts produced in earlier phases (such as the discovery plans, visual layouts, and prototype READMEs) to ensure consistency.
- Validate that the current phase's work aligns with the requirements and constraints established in earlier phases.
- Do not remain idle; use any wait time to verify file existences, scan for unresolved placeholders, and check that status mappings are accurate.
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.
- 2d ago First seen · 41 lines · 23 tokens per session scan A e5b3aec18031
using-exploration-cycle is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 522 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
close-issue
Close a GitHub or GitLab issue with a summary comment.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
bbc-skill
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not…
team-coordination
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.