test-spec-gen

test-spec-gen is a skill for Claude Code from anombyte93/atlas-session-lifecycle. It costs 50 tokens per session (5,203 once invoked), scanned A, original, MIT.

A test-specification generator that explores a codebase and produces a structured document describing what should be tested. A test specification is a detailed checklist of test cases, and the generated format uses identifiers such as TC-001.

In plain words
What is it for?
Use `/test-spec-gen` to map an application, generate organized test cases, review the resulting specification, refine it, and optionally turn the cases into Trello cards.
Why use it?
It helps uncover missing coverage across pages, authentication, data, and other areas before implementation or release. It also separates planning and review from the later generation work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the atlas-session-lifecycle plugin — 6 skills shipped together

Good fit Use /test-spec-gen to map an application, generate organized test cases, review the resulting specification, refine it, and optionally turn the cases into Trello cards.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anombyte93/atlas-session-lifecycle/test-spec-gen
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 anombyte93/atlas-session-lifecycle --skill test-spec-gen
Clone the repo
git clone --depth 1 https://github.com/anombyte93/atlas-session-lifecycle

Made for: Claude Code.

Or install atlas-session-lifecycle, the plugin that ships this one along with the rest of its 6 skills.

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 test-spec-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/anombyte93/atlas-session-lifecycle/test-spec-gen.svg)](https://agentmods.dev/skills/anombyte93/atlas-session-lifecycle/test-spec-gen)
Your own site
<a href="https://agentmods.dev/skills/anombyte93/atlas-session-lifecycle/test-spec-gen"><img src="https://agentmods.dev/badge/skills/anombyte93/atlas-session-lifecycle/test-spec-gen.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,203 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 warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 85
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
  • high Agent Snooping · line 131
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
  • high Privilege Escalation · line 260
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 268
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.05203
Opus 5 $0.00025 $0.02601
Sonnet 5 $0.00010 $0.01041
Haiku 4.5 $0.00005 $0.00520

Measured 8d ago against content hash 6ebae1f73f20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-spec-gen 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 8d 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.

.claude/skills/test-spec-gen/SKILL.md · 839 lines

How it starts

The opening of the file, as written. The whole thing — 839 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Specification Generator Skill

Generates production-grade test specifications for any application through multi-agent exploration, research, and specialist generation.

UX Contract

  1. User runs /test-spec-gen [optional-filter]
  2. Skill enters plan mode, presents approach, gets approval
  3. Executes multi-agent pipeline silently
  4. Presents test spec document for review
  5. Iterates with quick-clarify until satisfied
  6. Offers Trello card conversion

Phase 0: Plan Mode Entry (CRITICAL)

HARD GATE: Do NOT proceed with any exploration, research, or generation until plan mode is approved.

Upon invocation:

  1. Read existing codebase to understand project type (web/desktop/mobile)
  2. Present the multi-agent approach with estimated agent count
  3. Ask user approval to proceed
  4. Only AFTER approval, begin the exploration phase

Plan Mode Presentation Template

# Test Specification Generator

I will generate a comprehensive test specification for this project using multi-agent orchestration:

## Discovery Phase (5 parallel agents)
- Agent 1: Routes & Pages exploration
- Agent 2: Auth & RBAC mapping
- Agent 3: Data & Backend analysis
- Agent 4: Framework & Config discovery
- Agent 5: Navigation & UX flows

## Research Phase
- /research-before-coding based on discovery findings

## Generation Phase (5 specialist agents)
- Domains determined from exploration + research
- Each generates TC-XXX formatted test cases

## Verification Phase
- Doubt agent review for maintenance burden prevention
- Traceability matrix generation

## Output
- Hermes-style test specification document
- Optional Trello card conversion via /trello-test

Proceed?

EnterPlanMode Trigger

Call EnterPlanMode() immediately after UX Contract section with this prompt:

Generate test specification for [project_name] using multi-agent orchestration:

1. Discovery: 5 parallel explore agents map codebase
2. Research: /research-before-coding for best practices
3. Generation: 5 specialist agents create TC-XXX test cases
4. Verification: Doubt agent review + traceability matrix
5. Output: Test spec doc + optional Trello conversion

Read the full file on GitHub · 839 lines

Files

What ships with it

2 files 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. 8d ago First seen · 839 lines · 50 tokens per session scan A 6ebae1f73f20

Subscribe to this mod's changes

test-spec-gen is a skill published in the GitHub repository anombyte93/atlas-session-lifecycle (87 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 5,203 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.