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.
npx skills add anombyte93/atlas-session-lifecycle --skill test-spec-gengit clone --depth 1 https://github.com/anombyte93/atlas-session-lifecycleWrote 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.
[](https://agentmods.dev/skills/anombyte93/atlas-session-lifecycle/test-spec-gen)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00050 | $0.05203 |
| Opus 5 | $0.00025 | $0.02601 |
| Sonnet 5 | $0.00010 | $0.01041 |
| Haiku 4.5 | $0.00005 | $0.00520 |
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.
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
- User runs
/test-spec-gen [optional-filter] - Skill enters plan mode, presents approach, gets approval
- Executes multi-agent pipeline silently
- Presents test spec document for review
- Iterates with quick-clarify until satisfied
- 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:
- Read existing codebase to understand project type (web/desktop/mobile)
- Present the multi-agent approach with estimated agent count
- Ask user approval to proceed
- 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
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.
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.
- 8d ago First seen · 839 lines · 50 tokens per session scan A 6ebae1f73f20
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.
Other skills, from other repositories
agent-teams
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement.
base
Universal coding patterns, constraints, TDD workflow, atomic todos.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.
flutter
Flutter development with Riverpod state management, Freezed, gorouter, and mocktail testing.
android-kotlin
Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.