probe SKILL.md skillA

probe from pantheon-org/tekhne is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pantheon-org/tekhne/probe@git:20261007.83cf275

Pins git:20261007.83cf275 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pantheon-org/tekhne
Path
skills/software-engineering/probe/SKILL.md
Versions recorded
3
Latest version
git:20261007.83cf275, committed Oct 7, 2026
First version recorded
Apr 11, 2026
Size
12,163 bytes
Repository stars
10
License
MIT

Safe-to-fail experiment for Complex domain problems where cause-effect is only visible in retrospect. Two-phase: foreground qualify → background probe → sense result. Use when: probe, safe-to-fail, test hypothesis, experiment with hypothesis, Complex domain with hypothesis. NOT for brainstorming (use brainstorm) or known cause-effect (use investigate).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Probe

Safe-to-fail experiment in Complex domain. Cause-effect only visible in retrospect — probe to sense patterns, not to prove.

**Probing:** **$ARGUMENTS**

Check for handoff context: if `$ARGUMENTS` references a `probe-to-probe-llm.md` file, load it before Phase 1 — carried context accelerates qualification.

## ⚠️ AskUserQuestion Guard

**CRITICAL**: After EVERY `AskUserQuestion` call, check if answers are empty/blank. Known harness bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

**If answers are empty**: DO NOT proceed with assumptions. Instead:
1. Output: "⚠️ Questions didn't display (known harness bug outside Plan Mode)."
2. Present the options as a **numbered text list** and ask user to reply with their choice number.
3. WAIT for user reply before continuing.

## Phase 1: Qualify (foreground — MANDATORY)

**ENTRY GATE: Phase 2 does not start until Phase 1 is complete. No bypass path exists.**

### 1.1 Parse hypothesis

Extract from `$ARGUMENTS` or handoff context:
- Hypothesis statement (what you believe might be true)
- Enabling constraints already known (carry forward from prior cycles — do NOT rediscover)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pantheon-org/tekhne/probe@sha256:6d3d85d465850794

The line at the top of this page pins the label git:20261007.83cf275, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ntzdgn23ynsitslt.svg)](https://markdownregistry.com/a/art_ntzdgn23ynsitslt)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Apr 11, 2026 and Oct 7, 2026, about one every 89 days.

versioncommittedcommitsizeaudit
git:20261007.83cf275 latest2026-10-07 83cf275 12,163 BA view · diff
git:20261002.e6369ee2026-10-02 e6369ee 12,177 BA view · diff
git:20260411.33e05462026-04-11 33e0546 9,789 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12163 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

pantheon-org/tekhne · 10 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ntzdgn23ynsitslt
GET https://markdownregistry.com/api/v1/resolve?ref=pantheon-org/tekhne/probe
GET https://markdownregistry.com/api/v1/blob/6d3d85d465850794d90f40ad29ac94fc395043f5ff1693fbe0627b0551175325

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from pantheon-org/tekhne

AGENTS.md AGENTS.md file
pantheon-org/tekhne · AGENTS.md
git:20261021.d128b5f · audit A · 10 stars
CLAUDE.md CLAUDE.md file
pantheon-org/tekhne · CLAUDE.md
git:20261007.fce3c8c · audit B · 10 stars
agents-md SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/agents-md/SKILL.md · Create and maintain AGENTS.md documentation for simple projects, complex monorepos, deterministic discovery, scoped…
git:20261004.cc33b37 · audit A · 10 stars
cache-audit SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/cache-audit/SKILL.md · Audit your Claude Code setup against prompt caching best practices. Checks ordering, tool stability, dynamic content…
git:20260710.a38941a · audit A · 10 stars
context-radar-audit SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/context-radar-audit/SKILL.md
git:20260928.242d7c2 · audit B · 10 stars
create-context SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/create-context/SKILL.md · Create the baseline session context from the in-folder of raw project documents, classifying each file by priority…
git:20261007.83cf275 · audit A · 10 stars
guided-interview SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/guided-interview/SKILL.md · Conduct a structured, one-question-at-a-time interview to explore a specific topic or decision — each question offers…
git:20260824.4a8d48e · audit A · 10 stars
handover-document-creator SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/handover-document-creator/SKILL.md
git:20261007.1762166 · audit B · 10 stars
load-context SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/load-context/SKILL.md · Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session…
git:20261007.83cf275 · audit A · 10 stars
opencode-build-plugins SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/build-plugins/SKILL.md · Create OpenCode plugins using the opencode-ai/plugin SDK. Use when user wants to build a plugin, extend OpenCode…
git:20260314.95ea1b2 · audit A · 10 stars
opencode-build-tool SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/build-tool/SKILL.md · Build custom tools and plugins using the OpenCode SDK packages. Use when creating custom tools, implementing tool…
git:20260314.95ea1b2 · audit A · 10 stars
opencode-configure SKILL.md skill
pantheon-org/tekhne · skills/agentic-harness/opencode-toolkit/configure/SKILL.md · Configure OpenCode via opencode.json and AGENTS.md with deterministic provider setup, model selection, permission…
git:20261004.cc33b37 · audit A · 10 stars

Every file in pantheon-org/tekhne

Other files named probe

probe SKILL.md skill
jongwony/epistemic-protocols · epistemic-cooperative/skills/probe/SKILL.md · Something feels off and the user cannot name what is stuck: the user can then say what it is — a shown candidate, their…
git:20261015.672e932 · audit A · 173 stars
probe SKILL.md skill
arbiterforge/codearbiter · .github/fixtures/codex-skill-resources/skills/probe/SKILL.md · Report this absolute source path, then read the nested routine.
git:20260824.44989c5 · audit A · 149 stars
probe SKILL.md skill
simota/agent-skills · probe/SKILL.md · Integrating OWASP ZAP/Burp Suite/Nuclei, planning penetration tests, executing DAST, and scanning for vulnerabilities…
git:20261009.1e21383 · audit A · 93 stars
probe SKILL.md skill
mozership/probe · skills/probe/SKILL.md · Write, run and debug Probe workflows, the YAML files the `probe` CLI runs to test and monitor HTTP APIs, gRPC services…
git:20261018.a043ddd · audit A · 13 stars
probe SKILL.md skill
scriptedalchemy/agent-bundle · packages/agent-bundle/tests/fixtures/host-install/src/skills/probe/SKILL.md · Confirm that the host-install proof fixture was discovered.
git:20260902.9514cec · audit A · 11 stars
probe SKILL.md skill
scriptedalchemy/agent-bundle · packages/agent-bundle/tests/fixtures/host-install-portable/src/skills/probe/SKILL.md · Confirm that the portable host-install proof fixture was discovered.
git:20260902.9514cec · audit B · 11 stars
probe SKILL.md skill
uze-sh/uze · conformance/_fixtures/parity/native/plugins/kit/skills/probe/SKILL.md · Parity probe skill. Use when asked to run the parity probe.
git:20260929.10e5878 · audit A · 3 stars
probe SKILL.md skill
uze-sh/uze · conformance/_fixtures/parity/uze/plugins/kit/skills/probe/SKILL.md · Parity probe skill. Use when asked to run the parity probe.
git:20260929.10e5878 · audit A · 3 stars

Browse by kind, by grade A, or by owner.