qa-plan

A risk-based testing planner that decides what parts of an application to test first, before detailed testing begins.

In plain words
What is it for?
Use it to inspect an app, rank areas as P0, P1, or P2, define what counts as finished, and create a test charter for exploration.
Why use it?
It focuses testing effort on areas where a failure would cause the most harm and is most likely to occur, rather than treating every area equally.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/victoraguilarsantamariadev/qa-explore/qa-plan
Any agent
npx skills add victoraguilarsantamariadev/qa-explore --skill qa-plan
Clone the repo
git clone --depth 1 https://github.com/victoraguilarsantamariadev/qa-explore

Made for: Claude Code, Codex.

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00120 $0.01183
Opus 5 $0.00060 $0.00592
Sonnet 5 $0.00024 $0.00237
Haiku 4.5 $0.00012 $0.00118

Measured yesterday against content hash 058646044f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-plan 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (engine/qa-plan.workflow.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/qa-plan/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qa-plan

Top QA teams don't test everything equally — they test by risk. qa-plan is the upfront half of the process: it decides what to test and in what order before a single expensive explore agent runs, so effort lands on the surface where a bug would hurt most and is most likely.

recon the app → per area: IMPACT (blast radius if it breaks) × LIKELIHOOD (how fragile / how changed)
             → risk score (deterministic) → rank P0 / P1 / P2
             → acceptance ("done") per area
charter OUT  → test-plan.md (the plan a lead reviews)  [GATE: you approve/re-rank]
             → seeds qa-explore `areas` in PRIORITY ORDER (riskiest first)

🔒 The priority is deterministic

An agent judges impact and likelihood (1–5 each, with a written rationale) — but the risk score and P0/P1/P2 band are computed by rules (impact × likelihood), so the ranking is consistent and defensible, not a vibe. Same judgements → same plan. (Same principle as qa-gate: the model assesses, the rules rank.)

The default risk rubric (configurable in plan)

  • impact 1–5: blast radius if this area is broken — money/data/security/legal at the top, cosmetic at the bottom.
  • likelihood 1–5: how likely it is broken — new/changed code, complex flows, past-bug hotspots, many integrations rank high.
  • risk = impact × likelihood (1–25). Bands (defaults): P0 ≥ 15, P1 8–14, P2 < 8.
  • Each area gets an acceptance line ("done" = the concrete happy path + the key negative/edge case that must hold) so the explore pass and the gate share one definition of success.

Engine (invoke via the Workflow tool; do not inline)

  • ${CLAUDE_PLUGIN_ROOT}/skills/qa-plan/engine/qa-plan.workflow.js

(If $CLAUDE_PLUGIN_ROOT is unset, the skill is at ~/.claude/skills/qa-plan — resolve the engine path relative to this SKILL.md.)

Prerequisites

  • The same qa.config.json qa-explore uses (baseUrl, login, etc.). Optional plan block: bands (P0/P1 thresholds), outFile (default test-plan.md), changed (a list/paths of what changed this release, to raise likelihood on touched areas), release label.

Read the full file on GitHub · 51 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. yesterday First seen · 51 lines · 120 tokens per session scan A 058646044f33

Subscribe to this mod's changes

qa-plan is a skill published in the GitHub repository victoraguilarsantamariadev/qa-explore (2 stars, last pushed 29d ago), licensed MIT. It adds 120 tokens to every session and 1,183 once invoked, about $0.0006 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.