What is spectre-create_test_guide?

A guide for writing a manual test checklist for completed software changes. Manual testing means a person follows the steps to check that a feature works, rather than running automated tests.

Use it after implementing and validating a feature to prepare a risk-focused human QA pass for its main flows, integrations, and user roles.

It helps teams check the parts most likely to fail without creating an unnecessarily large checklist or confusing manual testing with automated testing.

spectre-create_test_guide — Skill for Claude Code by joenandez

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 joenandez/spectre --skill spectre-create_test_guide

Clone the repo

git clone --depth 1 https://github.com/joenandez/spectre

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_test_guide/github.svg)](https://agentmods.dev/skills/joenandez/spectre/spectre-create_test_guide)

Your own site

<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-create_test_guide"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_test_guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-create_test_guide"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_test_guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 904 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.00904
Opus 5	$0.00035	$0.00452
Sonnet 5	$0.00014	$0.00181
Haiku 4.5	$0.00007	$0.00090

Measured 4d ago against content hash a2d50b10da20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spectre-create_test_guide 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.

plugins/spectre-codex/skills/spectre-create_test_guide/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create_test_guide

Produce a manual testing guide, scaled to the change, that a human can run to validate the work. Input is the current task's changes; output is one checklist artifact.

Inputs

$ARGUMENTS — optional explicit feature name/root or descendant artifact, focus areas to emphasize, an explicit source-plan path, and --orchestrated when a parent workflow owns the next step.
Task context: features added/modified/removed, stack/environment, user personas, integration points/dependencies. Prioritize an explicitly passed source-plan path ahead of literal plan.md; otherwise read from canonical artifacts (scope.md, plan.md, tasks.json slices) and the diff. Use execute.md only to locate tasks.json; do not inline the full task graph.

Working Set

Reuse a managed FEATURE_ROOT only when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and follow Skill(spectre-feature-root) through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged.
Repair stale feature/root metadata in artifacts this workflow touches.
Read-only: explicitly supplied feature artifacts and the implemented diff.
Write: the single test-guide artifact only.

Outputs + DONE

Write to {FEATURE_ROOT}/testing/test_guide.md and begin immediately below the title with:

Feature: <feature-name>
Feature Root: .spectre/features/<feature-name>

DONE when:

Complexity classified Simple | Medium | Complex with a one-line rationale (Simple = smoke/happy-path + quick regression; Medium = edge cases, error handling, basic integration; Complex = advanced scenarios, performance, cross-feature, security).
Required sections present (always): Testing Overview (scope, environment, prerequisites) · Environment Setup (steps + verification) · Core Test Cases (primary functionality) · Results Documentation (how to record/report).
Optional sections included only when relevant: Known Issues & Limitations · Rollback Procedures (high-risk/prod) · Performance · Accessibility (UI/UX) · Cross-Browser/Device (frontend) · Data Validation · Security (auth/permissions/data-access).
Organized by user workflow/feature, not procedural phases; headers name the user goal.
Each checkbox is an action + verification pair (e.g. "Send POST to /api/users → verify 201 with user ID returned"), using [ ] for tracking; related steps grouped under one scenario; concrete test data (paths, names, shortcuts/UI elements in parens) included.
Depth scaled to change size (CSS tweak ≠ payment system); instructions runnable by someone unfamiliar with the code; no over-engineering for trivial changes.
A coverage summary returned: # workflows, # steps, estimated time, and the chosen complexity tier + rationale.

Read the full file on GitHub · 56 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.

4d ago Changed a2d50b10da20
9d ago First seen · 56 lines · 70 tokens per session scan A 2454828537df

Subscribe to this mod's changes

spectre-create_test_guide is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 904 once invoked, about $0.0003 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 2026-08-30.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

spectre-create_test_guide