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 shennawardana23/skillme --skill exploratory-testing-techniquesgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/exploratory-testing-techniques)<a href="https://agentmods.dev/skills/shennawardana23/skillme/exploratory-testing-techniques"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/exploratory-testing-techniques/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/shennawardana23/skillme/exploratory-testing-techniques"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/exploratory-testing-techniques.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 | $0.00105 | $0.01392 |
| Opus 5 | $0.00053 | $0.00696 |
| Sonnet 5 | $0.00021 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
exploratory-testing-techniques 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 9d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploratory Testing Techniques
Exploratory testing (ET), as defined by James Bach and Michael Bolton's Rapid Software Testing methodology, is simultaneous learning, test design, and test execution — the tester designs the next test based on what the last one revealed, rather than following a pre-written script. It is a disciplined skill, not "just clicking around": the discipline comes from charters, time-boxing, and oracles, not from a script.
Session-Based Test Management (SBTM)
Structure exploration so its value is traceable, per Jonathan Bach's Session-Based Test Management:
- Write a charter before the session starts:
Explore <area> with <resources/tools> to discover <information>.Example: "Explore the discount-stacking checkout flow with expired and near-expiry promo codes to discover incorrect price calculations." - Time-box the session — 60-120 minutes is typical. Longer sessions lose focus; shorter ones don't give exploration room to follow leads.
- Explore and take notes continuously — not just when you find a bug. Note what you tried, what you expected, what happened, and anything that felt off but wasn't clearly wrong yet.
- Log bugs immediately, with repro steps, while the state is still in
front of you — see
bug-triage-and-severity-classificationfor what happens to the report next. - Write a session report / debrief: charter, session duration, % of time on-charter vs. opportunity testing (following an unplanned but promising lead), bugs found, issues/questions raised, areas still uncovered. A session without a report is testing debt — the value of ET is in what's traceable afterward, not just in the tester's memory.
Oracles: how you judge "is this actually wrong"
Without a full spec, use Michael Bolton's HICCUPPS(F) heuristic to decide whether an observed behavior is a bug:
- History — does it behave differently than it used to?
- Image — does it embarrass the company/product's reputation?
- Comparable products — do similar products/features behave differently in a way that suggests this is wrong?
- Claims — does it contradict documentation, specs, or marketing claims?
- User expectations — would a reasonable user be surprised?
- Product — is it internally consistent with the rest of the product?
- Purpose — does it defeat the purpose the feature was built for?
- Statutes — does it violate a law/regulation (e.g. accessibility, data privacy)?
- Familiar problems — does it resemble a known bug pattern/class?
What ships with it
1 file 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.
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.
- 9d ago First seen · 114 lines · 105 tokens per session scan A d1a44333555a
exploratory-testing-techniques is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,392 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
fix-bug
Resolves a single bug from any starting evidence — Dash0 telemetry (span / log / web event / RUM error link), raw stack trace, error message, code pointer (file:line), screen recording, Linear ticket URL, or free-text symptom. Classifies the input, triages complexity (Phase 0.5) to pick between a fast lane and a full…
storybook
Scaffolds, audits, and tests Storybook stories for React (web) and React Native / Expo (native) component libraries. Generates three artefacts in two files per invocation: a visual regression .stories.tsx file containing a Default story (variants grouped into a single snapshot) and a Playground story (interactive args…
polish
Re-runnable pre-PR quality gate for the current branch. Composes two existing passes over the branch diff: a broad pr-reviewer pass (read-only review via the branch's open PR, which pr-reviewer requires) and a code-quality simplify pass (applies Class M mechanical refactors behind a confidence ≥ 90 % gate, reverting…
e2e-pr-stabilizer
Stabilizes or optimizes Playwright E2E tests on one PR via a local-first loop, then ratifies with a single CI run. Pulls Dash0 spans (git.pullrequestlink) as the historical baseline, then captures every iteration's evidence locally with --trace=on (same OTel exporter, same trace schema). Validation is empirical, not…
aw-setup
One-time (but safely re-runnable) setup flow that scaffolds a project's aw-tester aw-target: detects auth strategy, captures storage state, writes .claude/aw-targets/local.yml, and validates with a smoke spec. Re-runs detect the existing aw-target and only re-prompt for what broke or changed. Triggers on "/aw-setup"…