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 agentmods add commands/tercel/spec-forge/test-casesgit clone --depth 1 https://github.com/tercel/spec-forgeWhat 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 | $0.00032 | $0.02440 |
| Opus 5 | $0.00016 | $0.01220 |
| Sonnet 5 | $0.00006 | $0.00488 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
test-cases 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.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior QA engineer with deep expertise in test case design, coverage analysis, and multi-dimensional testing methodology.
Your task is to generate a structured test case set for: $ARGUMENTS
Step 0: Parse Arguments
Parse $ARGUMENTS to determine:
--formalflag: If present, include formal management sections (environment, roles, schedule, defect management)- Target: The remaining argument after removing
--formal(if any)
| Argument Pattern | Formal Mode | Target |
|---|---|---|
--formal user-auth |
Yes | user-auth |
user-auth |
No | user-auth |
--formal @src/services/pay.ts |
Yes | @src/services/pay.ts |
@src/services/pay.ts |
No | @src/services/pay.ts |
--formal (no target) |
Yes | Full scan |
| (empty) | No | Full scan |
Step 1: Project Context Scanning
1.1 Basic Project Scan
- Use Glob to scan the project directory tree
- Read the project README.md if it exists
- Scan
docs/for existing documents - Detect (do NOT read) matching upstream documents: check if
docs/*/srs.mdanddocs/*/tech-design.mdrelated to the target exist - Use Grep to identify:
- Project frameworks: Express, FastAPI, Spring Boot, Gin, NestJS, Click, Cobra, Commander, React, Vue, Svelte, Angular, LangChain, etc.
- Testing frameworks: Jest, pytest, JUnit, Go test, Vitest, etc.
- Database/ORM: Prisma, TypeORM, SQLAlchemy, GORM, Mongoose, etc.
- Auth patterns: JWT, OAuth, passport, auth middleware/decorators
- Test configuration files, CI/CD pipelines
1.2 Determine Input Mode
| Condition | Mode |
|---|---|
Target starts with @ and points to a .md spec file |
Spec Mode |
Target starts with @ and points to source code |
Code Mode |
| Target is a feature name or empty | Scan Mode |
1.3 Extract Testable Units
Scan Mode (full project):
- Scan ALL source files to extract testable units:
- Routes/endpoints: HTTP method, path, parameters, response patterns
- Functions/methods: name, parameters, return type, branch logic
- Components: props, events, state, lifecycle
- Commands: name, subcommands, flags, handler
- Tool definitions: name, trigger condition, parameters
- Models: schema, relationships, constraints
- Record for each unit: name, type, file path, line number, dependencies
- Scan existing test files to identify which units already have tests
- Build the Functional Inventory
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.
- yesterday First seen · 229 lines · 32 tokens per session scan A 86854b18bcf4
test-cases is a command published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,440 once invoked, about $0.0002 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.
Other commands, from other repositories
ai-engineer-review
Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architecture, code quality, skills/commands/hooks setup, redundancy, gaps, and concrete improvement suggestions.
architecture-docs
Generate architecture documentation — from a quick Mermaid diagram to full system overview with data flow, component relationships, and architecture decision records (ADRs).
prompt-test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
test-coverage
Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.
toolkit
Show available skills, agents, and commands — and recommend which to use based on the current repo and task. Helps new users discover what capabilities are available.
diff-explain
Explain a git diff or branch comparison in plain language. Describes the intent behind changes, not just what files were modified. Useful for MR reviews and catching up.