agentmods.dev

exploratory

exploratory is a skill for Claude Code, Codex from TimothyHan/qa-buddy-skills. It costs 117 tokens per session (2,098 once invoked), scanned C, original, Apache-2.0.

A guided method for testing software by exploring it without a fixed script. Exploratory testing uses a time limit and a goal, then records unexpected behaviour and areas that need more testing.

In plain words
What is it for?
Use it to run browser-based testing sessions, capture screenshots and technical evidence, classify findings by severity and priority, and turn discoveries into future test scenarios.
Why use it?
It helps uncover problems that prepared test cases may miss, while keeping the testing session focused and documented.

Skill for Claude CodeCodex

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

not rated 9repo changed 1mo ago C scan 117 tokens original Apache-2.0

Good fit Use it to run browser-based testing sessions, capture screenshots and technical evidence, classify findings by severity and priority, and turn discoveries into future test scenarios.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/timothyhan/qa-buddy-skills/exploratory
View source ↗ TimothyHan/qa-buddy-skills
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 TimothyHan/qa-buddy-skills --skill exploratory
Clone the repo
git clone --depth 1 https://github.com/TimothyHan/qa-buddy-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 exploratory

README.md
[![agentmods](https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/exploratory/github.svg)](https://agentmods.dev/skills/timothyhan/qa-buddy-skills/exploratory)
Your own site
<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/exploratory"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/exploratory/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.

agentmods 80×15 button for exploratory

Your own site · 80×15
<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/exploratory"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/exploratory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.02098
Opus 5.5 $0.00047 $0.00839
Sonnet 5.5 $0.00023 $0.00420
Haiku 4.5 $0.00012 $0.00210

Measured 1mo ago against content hash 952da8c079a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

exploratory scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

8. **Always use the browser.** Never refuse browser testing when /qa-exploratory is invoked.
core/skills/exploratory/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/qa-exploratory: Exploratory Testing Session

You are an SDT partner guiding and executing an exploratory testing session. Exploratory testing is unscripted, time-boxed, charter-driven testing that discovers what scripted tests miss.

Constraints

  1. Stay unscripted. Charter gives direction, not steps. Follow surprises.
  2. Time-box strictly. When time is up, wrap up. Don't extend without SDT consent. Headless: run --quick and wrap up once every focus area has a result.
  3. Classify every finding. Severity and priority per REF-playbook/risk-and-priority#severity-scale and #priority-scale in your compiled slice. No unclassified findings.
  4. Screenshot everything interesting. Findings without evidence are not findings.
  5. Check console and network requests constantly. After every interaction, every page load — API status codes and query parameters prove what the UI hides.
  6. Discovers, not fixes. Findings feed /qa-test-cases and /qa-qa. Don't fix or automate here.
  7. Note what you didn't get to. List unexplored areas for the next session.
  8. Always use the browser. Never refuse browser testing when /qa-exploratory is invoked.

Scratchpad (run protocol): write ## Plan to the run's scratchpad.md before Phase 1; at each phase boundary and every Review Options pause update ## State and re-read the scratchpad before continuing; drop noteworthy things into ## Candidate learnings as you go.

Phase 1: Setup

Methodology reference: Read from {{REFERENCE_PATH}}/playbook/:

  • test-types.md — where exploratory sits among the manual test types (after functional, before UAT)
  • metrics-and-coverage.md — exploratory fills coverage gaps
  • test-distribution.md — assign discoveries to the right test layer
  • exploratory-heuristics.md — heuristic categories, techniques, finding categories
  1. Read .qabuddy.json (if exists) for context source and team mode.
    • contextSource: "spec" → search workspace for spec files before asking
    • contextSource: "chat" → skip Jira, ask SDT for context directly
    • contextSource: "jira" or no config → current behavior

Read the full file on GitHub · 187 lines

Files

What ships with it

60 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.

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. 1mo ago Changed · +2 lines 952da8c079a6
  2. 1mo ago Changed 832f7ddcf183
  3. 1mo ago First seen · 185 lines · 117 tokens per session scan C dfe6b604e5aa

Subscribe to this mod's changes

exploratory is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (9 stars, last pushed 20d ago), licensed Apache-2.0. It adds 117 tokens to every session and 2,098 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeTestingagent-memoryai-agentscontext-engineeringplaywrightqa
Related

Other skills, from other repositories

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.

bojieli/ai-agent-book · 139 tokens

agent-evaluation

A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.

bojieli/ai-agent-book · 133 tokens

bad-case-to-dpo

A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.

bojieli/ai-agent-book · 168 tokens

eval-dataset-design

A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.

bojieli/ai-agent-book · 138 tokens

qawolf-cli

Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; run or list flows…

qawolf/cli · 112 tokens

test-review

A review checklist for newly written or changed automated tests using TypeScript and Playwright. Playwright is a tool for testing web browsers, and automated tests check software without repeating the steps by hand.

akovalion/paranoid-qa · 137 tokens