agent-harness-explorer

agent-harness-explorer is a skill for Claude Code, Codex from microsoft/cat-agent-skills. It costs 89 tokens per session (1,350 once invoked), scanned A, original, MIT.

A guide for inspecting what the current AI agent environment can do. It uses runtime checks to document visible tools, installed libraries, and other capabilities, while distinguishing observed facts from uncertain ones.

In plain words
What is it for?
Checking available capabilities, finding suitable libraries for documents or charts, capturing a baseline, comparing it with a later snapshot, listing saved snapshots, and exporting the latest one.
Why use it?
Assumptions about available tools or libraries can lead to wasted work or incorrect instructions. A recorded snapshot makes it easier to compare the environment later.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Checking available capabilities, finding suitable libraries for documents or charts, capturing a baseline, comparing it with a later snapshot, listing saved snapshots, and exporting the latest one.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/cat-agent-skills/agent-harness-explorer
About the project

microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.

microsoft/cat-agent-skills · 64 stars · on GitHub

Install

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.

Any agent
npx skills add microsoft/cat-agent-skills --skill agent-harness-explorer
Clone the repo
git clone --depth 1 https://github.com/microsoft/cat-agent-skills

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.

agentmods badge for agent-harness-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/agent-harness-explorer.svg)](https://agentmods.dev/skills/microsoft/cat-agent-skills/agent-harness-explorer)
Your own site
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/agent-harness-explorer"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/agent-harness-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 14
    Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
    Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01350
Opus 5 $0.00044 $0.00675
Sonnet 5 $0.00018 $0.00270
Haiku 4.5 $0.00009 $0.00135

Measured 8d ago against content hash 9d84369899c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-harness-explorer 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 8d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/archive_snapshot.py, scripts/canonicalize_snapshot.py, scripts/capture_snapshot.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

submissions/agent-harness-explorer/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Agent Harness Explorer. You help makers discover, document, and monitor the capabilities of an agent harness. Always prefer runtime observation over assumptions, and clearly separate what you observed from what you believe a platform supports.

When to use this skill

Use it when the user asks any of:

  • "What can this harness do?" / "Inspect the harness."
  • "Which Python libraries are installed?" / "What should I use to create Word documents / Excel files / PDFs / charts?"
  • "Capture a snapshot." / "Remember this snapshot." / "Save this as my baseline."
  • "Compare with my previous snapshot / baseline." / "What changed since last week?"
  • "List remembered snapshots." / "Export the latest snapshot."

Golden rules

  1. Observe, don't assume. Run the probes; never invent capabilities.
  2. Never mark something unsupported because a probe failed. Use unknown, unverified, or not-visible instead.
  3. Passive by default. Only run active-safe probes after a brief heads-up, and never run active-sensitive actions (installs, arbitrary shell/network) unless the user explicitly directs you. See references/safety-boundaries.md.
  4. Redact secrets. Never record or display tokens, passwords, connection strings, private keys, or full environment values.
  5. Memory is the default store, but is user-specific. Encourage exporting JSON + Markdown for durable or shared retention.

Workflow

Inspect (no save)

  1. Run python scripts/capture_snapshot.py --catalog references/python-library-catalog.yaml --out snapshot.json. Add --active-safe only after telling the user you'll create+delete a temp file, run a benign command, and make one HTTPS request to pypi.org.
  2. For tool/skill/MCP visibility, enumerate what you (the agent) can see in your own context, write it to observations.json in the shape documented in scripts/inspect_tools.py, and pass --tools observations.json. If you cannot enumerate them, omit it — they'll be recorded as not-visible.
  3. Render the report — by default generate only the self-contained HTML:
    • python scripts/generate_html_report.py snapshot.json --out report.html (themed HTML combining the capability report and library inventory — ideal for sharing or browsing outside the agent)
    • Generate the Markdown outputs only when the user explicitly asks for Markdown:
      • python scripts/generate_markdown_report.py snapshot.json --out report.md
      • python scripts/generate_library_inventory.py snapshot.json --out inventory.md
  4. Summarize results for the user and surface any uncataloged packages.

Read the full file on GitHub · 111 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.

  1. 8d ago First seen · 111 lines · 89 tokens per session scan A 9d84369899c4

Subscribe to this mod's changes

agent-harness-explorer is a skill published in the GitHub repository microsoft/cat-agent-skills (64 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,350 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens