rpi-explore-release

rpi-explore-release is a skill for Claude Code from juan294/cc-rpi. It costs 31 tokens per session (1,445 once invoked), scanned A, original, MIT.

An exploratory testing workflow that gives independent testers focused tasks, called charters, against one fixed release candidate. It checks how the deployed product behaves during interactions and recovery, beyond what repeatable automated tests cover.

In plain words
What is it for?
Use it to explore a release candidate before approval, gather evidence for the release decision, and test real user flows and failure recovery.
Why use it?
It can find interaction and recovery failures that scripted checks do not exercise, while keeping the tested release candidate unchanged.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the cc-rpi plugin — 36 skills, 19 commands, 2 hooks shipped together

Good fit Use it to explore a release candidate before approval, gather evidence for the release decision, and test real user flows and failure recovery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juan294/cc-rpi/rpi-explore-release
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 juan294/cc-rpi --skill rpi-explore-release
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Made for: Claude Code.

Or install cc-rpi, the plugin that ships this one along with the rest of its 36 skills, 19 commands, 2 hooks.

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 rpi-explore-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/juan294/cc-rpi/rpi-explore-release/github.svg)](https://agentmods.dev/skills/juan294/cc-rpi/rpi-explore-release)
Your own site
<a href="https://agentmods.dev/skills/juan294/cc-rpi/rpi-explore-release"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/rpi-explore-release/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 rpi-explore-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/juan294/cc-rpi/rpi-explore-release"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/rpi-explore-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,445 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.
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 $0.00031 $0.01445
Opus 5 $0.00015 $0.00723
Sonnet 5 $0.00006 $0.00289
Haiku 4.5 $0.00003 $0.00145

Measured 4d ago against content hash f0a20e208a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rpi-explore-release 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 4d 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.

generated/claude/skills/rpi-explore-release/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The request is supplied as literal arguments: $ARGUMENTS

Exploratory Release Charters

Independent, fresh-context exploratory testing of a fixed release candidate. This is Wave B of the E2E Pro release-verification system (release playbook) — the cheap, high-yield layer that targets interaction and recovery failures deterministic suites miss.

It complements, and does not replace:

  • rpi-pre-launch + rpi-remediate — static, code-as-written audit. Charters exercise the deployed candidate's behavior instead.
  • rpi-release — the tagging authority. Charters feed evidence into the release gate; they never tag.

Read the release playbook Section 6 (Wave B) for the full decision detail. This command is the executable protocol.

Input

rpi-explore-release <LAST_RELEASE_REF> <CANDIDATE_SHA_OR_DIGEST>

If arguments are omitted, infer <LAST_RELEASE_REF> from the last release tag and <CANDIDATE_SHA> from the fixed candidate under release. Verify both against the request and actual candidate before assigning charters; ask only if the identity cannot be established.

Step 1: Fix the candidate and read the diff

  1. Confirm the candidate is immutable (a specific SHA, tag, or artifact digest), not a moving branch. Stop if it is mutable (playbook D06).

  2. Compute the change surface:

    git log --oneline <LAST_RELEASE_REF>..<CANDIDATE_SHA>
    git diff --stat <LAST_RELEASE_REF>..<CANDIDATE_SHA>
    
  3. Map changed paths to user-facing capabilities, actors, surfaces, states, and external seams. Do not trust stale docs — inspect the actual routes, jobs, and providers touched.

Step 2: Generate charters

Size the charter set to the diff — do not pad the count:

  • tiny, isolated diff → 1 charter;
  • normal release → 2–4 charters;
  • more only for distinct high-risk capability groups.

Prioritize: outward writes, new/changed state transitions, vendor or retry behavior, authorization boundaries, changed copy that promises an outcome, new multi-surface flows, and recent escape classes.

Read the full file on GitHub · 148 lines

Files

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.

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. 4d ago First seen · 148 lines · 31 tokens per session scan A f0a20e208a0f

Subscribe to this mod's changes

rpi-explore-release is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 1,445 once invoked, about $0.0002 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 2026-09-06.

Related

Other skills, from other repositories

atf-testing

Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.

serac-labs/serac · 45 tokens

acceptance

A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.

cryndoc/polisade-orchestrator · 129 tokens

e2e-runner

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

ComeOnOliver/skillshub · 59 tokens

axiom-axe-ref

Use when automating iOS Simulator UI interactions beyond simctl capabilities. Reference for AXe CLI covering accessibility-based tapping, gestures, text input, screenshots, video recording, and UI tree inspection.

ComeOnOliver/skillshub · 45 tokens

playwright-stability

Make a Playwright E2E suite stable and realistic — kill flaky tests and authenticate like a real user via storageState (login once, reuse). Use when E2E tests are flaky, slow, re-login in every test, mock auth instead of using it, or when hardening a suite before relying on it.

LFTPadilla/agent-dev-kit · 70 tokens

axiom-ios-testing

Use when writing ANY test, debugging flaky tests, making tests faster, or asking about Swift Testing vs XCTest. Covers unit tests, UI tests, fast tests without simulator, async testing, test architecture.

ComeOnOliver/skillshub · 45 tokens