qa-edge-hunter

qa-edge-hunter is a skill for Claude Code from nguyenvanphituoc/shapeup-sdlc-plugin. It costs 174 tokens per session (4,671 once invoked), scanned C, original, MIT.

A post-testing skill for exploring edge cases—the unusual inputs, conditions, or failures outside a feature’s main path—after the initial evaluator passes. It follows Shape Up’s practice of checking the edges near the end of development.

In plain words
What is it for?
Use it to run exploratory checks on a working feature, record unexpected findings, and separate edge-case issues from required conformance failures.
Why use it?
A specification-based test may confirm the written requirements while overlooking behavior those requirements never mention. This pass finds such issues for later triage.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the shapeup-sdlc-plugin plugin — 17 skills, 11 commands, 4 hooks shipped together

Good fit Use it to run exploratory checks on a working feature, record unexpected findings, and separate edge-case issues from required conformance failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter
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 nguyenvanphituoc/shapeup-sdlc-plugin --skill qa-edge-hunter
Clone the repo
git clone --depth 1 https://github.com/nguyenvanphituoc/shapeup-sdlc-plugin

Made for: Claude Code.

Or install shapeup-sdlc-plugin, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 4 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 qa-edge-hunter

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter/github.svg)](https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter)
Your own site
<a href="https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter"><img src="https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter/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 qa-edge-hunter

Your own site · 80×15
<a href="https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter"><img src="https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/qa-edge-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,671 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00174 $0.04671
Opus 5 $0.00087 $0.02336
Sonnet 5 $0.00035 $0.00934
Haiku 4.5 $0.00017 $0.00467

Measured 9d ago against content hash bb9bb5e4e0ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

qa-edge-hunter scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Do not refuse the hunt, and do not invent a URL. Its write surface is
skills/qa-edge-hunter/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Edge Hunter — the post-PASS edge pass (v1.1)

Shape Up, Ch. 13: QA comes in toward the end, hunts edge cases outside the core, and its issues are nice-to-haves by default that the team triages. This skill is that role for the harness. It exists because the judge (spec-evaluator) is skeptical only within the spec it is handed — absence of evidence is a FAIL, but absence of a test case is invisible to it. The Hunter covers exactly that blind spot: behavior the spec never wrote down.

tech-lead: ... GATE L2 → EVAL → GATE L3 PASS ──► QA EDGE HUNT (you) ──► SHIP S.0 triage → L4
                                                  charters · hunts · ~ findings → ledger
            GATE L3 FAIL → fix round (never reaches you — conformance first, edges after)

Division of labor (a settled design decision, not a convention):

Tier Owner When
Derivable tests (boundaries, error codes, no-go breaches the spec implies) ba ## Test Surface + evaluator test-surface-conformance spec time / every EVAL
Exploratory edges (this skill) /qa-edge-hunter once, post-first-PASS

What the Hunter is and is not

Does Does NOT
Read EVAL-*.md to map covered territory — then hunt OUTSIDE it Re-probe anything the evaluator already graded
Charter edges via six fixed lenses, minus covered territory Author or extend ## Test Surface (that is the planner's retrofit-surface operation)
Execute charters against the running deliverable (session-based exploratory) Read-only speculate from code ("this looks racy") — every finding needs a live repro
Return each finding in the WorkResult's discoveries[], always ~ Promote ~ → must-have (PO/TL at SHIP S.0; severity-hint is advice, not a decision)
Emit qa/hunt-report.md — charters run/cut, findings by lens Render a verdict, score, or PASS/FAIL of any kind

Pure worker (harness rule: stateless workers, one stateful orchestrator). Its WorkOrder carries payload.feature, payload.spec_folder, payload.eval_report, payload.app_url, payload.kb_rules_path, and payload.ledger (the discovery ledger, READ-ONLY — covered-territory context so a hunt does not re-report what is already known). app_url is null when the deliverable is not served over HTTP — a CLI, a library, a batch job. That is a normal order, not a malformed one: drive the built entry point instead, exactly as the Test Surface's process rows do. Do not refuse the hunt, and do not invent a URL. Its write surface is .shapeup/<feature>/qa/** only. The Hunter never touches the discovery ledger itself — ingest appends its discoveries[] under a ## Discovered section, preserving single-writer mechanically.

Read the full file on GitHub · 344 lines

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. 9d ago First seen · 344 lines · 174 tokens per session scan C bb9bb5e4e0ba

Subscribe to this mod's changes

qa-edge-hunter is a skill published in the GitHub repository nguyenvanphituoc/shapeup-sdlc-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 174 tokens to every session and 4,671 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.