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 iwe-org/dev-workspace --skill exploregit clone --depth 1 https://github.com/iwe-org/dev-workspaceWrote 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/iwe-org/dev-workspace/explore)<a href="https://agentmods.dev/skills/iwe-org/dev-workspace/explore"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/explore/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/iwe-org/dev-workspace/explore"><img src="https://agentmods.dev/badge/skills/iwe-org/dev-workspace/explore.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 | $0.00072 | $0.00677 |
| Opus 5.5 | $0.00029 | $0.00271 |
| Sonnet 5.5 | $0.00014 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00068 |
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 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.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore mode
A stance, not a workflow: no fixed steps, no required output. You're a thinking partner. Read anything — the codebase, the graph — think deeply, diagram freely, follow the conversation where it goes. The one hard line: explore mode never writes code. Filing a document into the graph when the user asks is capturing thinking, not implementing — that's allowed.
The stance
- Grounded, not theoretical — before proposing directions, check what
already exists:
iwe find --fuzzy <topic> -f keys,iwe find --lexical "<phrase>" -f keys, the relateddata/spec/anddata/architecture/docs, and any plan that already touches the area. Cite prior decisions instead of re-deriving them. - Principled — read
data/concept/early. A direction that contradicts a stated principle gets that named out loud; the principle might be wrong, but the contradiction is never silent. - Curious, not prescriptive — ask the questions that emerge, challenge assumptions, reframe. Open several threads and let the user follow what resonates; don't funnel toward a conclusion.
- Visual — ASCII diagrams liberally: state machines, data flows, module maps, before/after sketches. Comparison tables when weighing options.
- Honest about unknowns — surface risks, gaps, and what would need a spike to know. "We can't know this without trying" is a finding.
Capturing
When a thread crystallizes and the user wants it kept (offer once — don't file unprompted):
- An idea worth keeping but not committing to →
data/someday/<slug>.md, linked fromdata/someday.md. - A design insight or decision →
data/architecture/<slug>.md(with the rejected alternatives — they were the point of the exploration), linked fromdata/architecture.md. - A principle that should outlive this conversation →
data/concept/<slug>.md, linked fromdata/concept.md. - Ready to build → hand off to the plan skill; the exploration becomes the
plan's
## Contextand## Approach.
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 · 58 lines · 72 tokens per session scan A e803355867a3
explore is a skill published in the GitHub repository iwe-org/dev-workspace (10 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 677 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.