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 bdfinst/agentic-dev-team --skill exploratory-testinggit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/exploratory-testing)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/exploratory-testing"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/exploratory-testing/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/bdfinst/agentic-dev-team/exploratory-testing"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/exploratory-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.01763 |
| Opus 5.5 | $0.00035 | $0.00705 |
| Sonnet 5.5 | $0.00017 | $0.00353 |
| Haiku 4.5 | $0.00009 | $0.00176 |
Grade A, and why
exploratory-testing 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 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.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploratory Testing
Overview
The QA Engineer in charter-driven "Chaos Specialist" mode. Given a charter and a running target (endpoint, CLI, feature), it probes with structured heuristics, captures telemetry on every probe, classifies defects, auto-triages critical findings, and writes an incremental report ending with runnable follow-up charters. It is bounded by a probe budget so a session always terminates.
Frameworks (charter quality, variable identification, state model, implicit-expectation lenses) live in knowledge/exploratory-testing-field-guide.md; this file is the protocol.
Constraints
- Probe a running target. This skill exercises live behavior — it does not read code to reason about bugs (that is
/triage's job once a defect is found). - Bounded. Stop at or before the probe budget (default 15) with a stated reason. Every probe counts.
- Incremental. Append each probe result to the report as it runs — a
/stopor budget exhaustion must still leave a usable partial report. - Auto-triage critical defects only, and never fix them — hand off to
/triage. - Be concise. Stream one line per probe to chat; the detail lives in the report.
Parse Arguments
--charter '<goal>'— required. Charter format:Explore [target] with [approach] to discover [concern].--probe-budget <n>— max probes (default 15).--invariants '<expr,...>'— per-probe invariants to validate; a violation is Critical-immediate.--no-adversarial— skip adversarial expansion (on by default).--force— proceed past a charter-quality warning without refining.- target — the URL/endpoint/command under test (from the charter or an explicit arg).
If --charter is absent, do not probe: emit exactly What should I investigate? Provide a charter: --charter '<goal>' and stop with no report.
Steps
1. Evaluate charter quality (before any probe)
Check the charter against the anti-patterns in the field guide (§1): too specific (a test case), too broad (infinite scope), missing with (no approach), missing to discover (no risk hypothesis). On a match, emit a one-line warning naming the anti-pattern and prompt: refine the charter, or re-run with --force. Do not probe until the charter is acceptable or --force is given.
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.
- 1mo ago First seen · 109 lines · 87 tokens per session scan A f42f7556c9f5
exploratory-testing is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 1,763 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.