What is midas-explore?

A note-taking tool for investigations that happen outside the project's normal nine-step workflow. It keeps session notes in a separate exploration folder without changing the project's workflow state.

Use it to investigate a problem, read sources named by the user, or explore an idea before turning the findings into a formal project task. End the session with its closing option.

It gives debugging and early scoping work a place to live without accidentally advancing project stages or changing product rules.

How okuzpe/midas-harness configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-explore/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/okuzpe/midas-harness

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-explore/github.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/midas-explore)

Your own site

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-explore"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-explore"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,129 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.01129
Opus 5.5	$0.00019	$0.00452
Sonnet 5.5	$0.00010	$0.00226
Haiku 4.5	$0.00005	$0.00113

Measured 2mo ago against content hash 04c2e5625a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

midas-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 2mo 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.

.agents/skills/midas-explore/SKILL.md · 80 lines

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.

midas-explore — investigation outside the pipeline

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Read paths.state first when checking sprint conflicts.

Paths: {runs}/ → paths.runs. Sessions live at {runs}/explore/<slug>/ (optional dir, like {runs}/qa/ — not in RUNS_SUBDIRS). Active pointer: {runs}/explore/.active (slug text). Git-visible only (ADR-003). Never advances stage or sprint gates.

Does / Does not

Does	Does not
Append notes across turns	Replace `/start-sprint` or phase skills
Fetch/read sources the user names	Write product rules silently
Propose `/midas-capture` on `--end`	Touch `paths.state` phase fields

Activation

At turn start, if {runs}/explore/.active exists and the user did not invoke /midas-explore or --end, run Carryover only (below). Otherwise load this full skill on explicit invoke.

Carryover (active session, normal user message)

Read {runs}/explore/<slug>/meta.yaml + notes.md (slug from .active).
Append under ## Notes (chronological): - [HH:MM] **User**: <summary> / - [HH:MM] **Agent**: <understanding + plan>
Route into Open questions / Hypotheses / Actionable items / Sources as needed.
Bump turn_count and last_activity in meta.yaml.
Reply to the user's question — do not re-dump the whole skill.

Start — `/midas-explore [topic]`

Conflict: if paths.state has a sprint status: active, AskQuestion once:
- "Keep sprint; cancel explore" (default)
- "Start explore anyway (sprint stays active; do not implement sprint tasks here)"
If .active already set → AskQuestion: close existing (--end --no-capture) and start new, or cancel.
Slug: kebab-case from topic (max 5 words); on collision append -2, -3.
Create {runs}/explore/<slug>/ from <paths.engine>/templates/explore-meta.yaml + explore-notes.md.
Write slug to {runs}/explore/.active.
Optional — lifecycle journal: node <paths.scripts>/lifecycle-journal.mjs explore_start --detail "<slug>" (fail-open).
Confirm in ≤5 lines: slug, path, how to end (/midas-explore --end).

Read the full file on GitHub · 80 lines

Changes

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.

2mo ago First seen · 80 lines · 48 tokens per session scan A 04c2e5625a14

Subscribe to this mod's changes

midas-explore is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,129 once invoked, about $0.0002 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.

Research

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

midas-harness: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

midas-explore — investigation outside the pipeline

Does / Does not

Activation

Carryover (active session, normal user message)

Start — `/midas-explore [topic]`

What this file has done since we first saw it

Other skills, from other repositories

local-ai-agents

systematic-debugging

next-cache-components-adoption

chat-pet-sprite-creation

cpu-profile-analysis

insight-error-page

midas-harness: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

midas-explore — investigation outside the pipeline

Does / Does not

Activation

Carryover (active session, normal user message)

Start — /midas-explore [topic]

What this file has done since we first saw it

Other skills, from other repositories

local-ai-agents

systematic-debugging

next-cache-components-adoption

chat-pet-sprite-creation

cpu-profile-analysis

insight-error-page

Start — `/midas-explore [topic]`