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.
git clone --depth 1 https://github.com/jonase47/ccprWrote 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/commands/jonase47/ccpr/p6-exploratory)<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-exploratory"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-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.
<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-exploratory"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-exploratory.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 | $0.00000 | $0.01638 |
| Opus 5.5 | $0.00000 | $0.00655 |
| Sonnet 5.5 | $0.00000 | $0.00328 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
p6-exploratory 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p6-exploratory – Exploratory Tests
Conducts unstructured, experience-based tests that automated tests and defined test cases do not cover. The goal is to find unexpected behaviours, usability issues, and hidden bugs that remain invisible in structured testing.
Argument: $ARGUMENTS = [focus area, e.g. "form validation", "mobile usage", "error handling"]
If provided: Focus exploratory tests on the specified area. If not provided: Read FEATURES.md and TESTPROTOCOL_FUNCTIONAL.md and select areas that have received little test attention so far. If any context is missing, ask about the application area.
0. Work-item adoption guard (ADR-0002 §8)
Usability findings from this command are optional backlog items (see Result) — this guard only applies if the user chooses to capture one.
Run python3 ~/.claude/scripts/workitems.py list.
- Non-empty array → the project uses the structured store. If the user opts to capture a usability finding as a backlog item, use the CLI (step 3 below) instead of BACKLOG.md prose.
[]and nodocs/workitems/directory → still on prose. Append to BACKLOG.md as before, if chosen. Emit one line: "Tip: runliftto adopt the structured work-item store."[]butdocs/workitems/exists → adopted store, just empty right now. Treat as adopted: use the CLI, not the prose fallback.
See docs/adr/ADR-0002-workitem-backend-contract.md for the adoption-guard rationale and the status vocabulary.
Execution
1. Read Context
Read the following files (if present):
- TESTPROTOCOL_FUNCTIONAL.md (what has already been tested → identify gaps)
- USER_JOURNEYS.md (personas as test perspectives)
- UX_CONCEPT.md (UX expectations – does the real behaviour deviate?)
- FEATURES.md (full scope of the application)
2. Delegation to QA-Tester Agent (Lead)
Delegate the exploratory tests to the qa-tester agent:
Run exploratory tests for: $ARGUMENTS Context: [Insert previous test results from TESTPROTOCOL_FUNCTIONAL.md, personas from USER_JOURNEYS.md]
Exploratory tests follow no fixed script. Instead, use the following heuristics and techniques:
A. Perspective Shifts Test from different user perspectives:
- Experienced user: Fast, unexpected actions (double-clicking, rapid scrolling, multiple tabs)
- Impatient user: Clicking buttons multiple times, abandoning forms, navigating back
- Curious user: All edge menus, hidden features, unusual combinations
- Error-prone user: Invalid inputs, very long texts, special characters, emojis, SQL injections
B. Explore State Boundaries
- What happens with empty states (no data, fresh account)?
- What happens with large amounts of data (performance, layout)?
- What happens during transitions between states (simultaneous actions)?
- What happens with interrupted actions (navigation mid-process)?
C. Technical Edge Cases
- Behaviour on slow connections / timeout
- Behaviour when external services are unavailable
- Behaviour with browser back button in critical flows
- Behaviour on session expiry mid-action
D. Usability Observations Also document observations that are not bugs but impair the user experience:
- Confusing error messages
- Unclear states (is the page still loading? Was the action successful?)
- Inconsistent behaviour between similar features
For each finding: description, reproduction steps, severity, category (Bug / Usability / Enhancement)
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 Changed 04542ee42352
- 1mo ago Changed · +2 lines 68dee91303ff
- 1mo ago Changed d68919ab76c4
- 1mo ago First seen · 128 lines · 0 tokens per session scan A eb286e9d1ba7
p6-exploratory is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,638 tokens. 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 commands, from other repositories
verify
Run verification loop to validate implementation.
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.
guard
Manually run the Hydra security and quality scan on specified files or directories.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
double-check
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.
playwright-setup
Verify Playwright CLI installation and create a .playwright/cli.config.json configuration file. Use when setting up browser automation, configuring Playwright, or user mentions "setup playwright", "configure browser testing", "install playwright".