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/saitarrun/devforge-ai/sdlc-testgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWhat 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 | $0.00031 | $0.00614 |
| Opus 5 | $0.00015 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
sdlc-test 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enterprise Test Suite Generation & Execution Command
This command allows developers and agents to scaffold, generate, and run specialized multi-tier test suites across every layer of the application.
Usage
/sdlc-test --suite unit # Run fast unit test suite with coverage
/sdlc-test --suite integration # Run Testcontainers database and queue integration tests
/sdlc-test --suite contract # Validate Pact / OpenAPI consumer contracts
/sdlc-test --suite e2e # Execute Playwright browser workflows
/sdlc-test --suite perf # Run k6 load, spike, and latency benchmark tests
/sdlc-test --suite chaos # Execute fault injection and network latency tests
/sdlc-test --suite fuzz # Run property-based security fuzzing
/sdlc-test --suite all # Execute full enterprise verification matrix
/sdlc-test --suite perf --target claims # Scaffold load test specifically for claims service
Process
- Test Matrix Resolution:
- Identifies target layers (Database, HTTP API, Browser UI, Queue, or Distributed Cluster).
- Deterministic Harness Setup:
- Spins up ephemeral test dependencies via Testcontainers or mock servers (MSW).
- Execution & Metric Assertion:
- Evaluates test outcomes, code coverage (>80%), p95 latency thresholds, and circuit-breaker tripping.
- Comprehensive Reporting:
- Emits structured pass/fail reports with trace artifacts, flamegraphs, and coverage heatmaps.
Output Format
### 🧪 Enterprise Test Matrix Execution Report
| Suite | Runner | Tests | Status | Key Metric / SLA |
|---|---|---|---|---|
| **Unit** | Vitest | 142 | ✅ Passed | 88.4% Branch Coverage |
| **Integration** | Testcontainers (Postgres + Redis) | 38 | ✅ Passed | 0 Stale Connections |
| **Contract** | Pact Broker | 12 | ✅ Passed | 100% Schema Parity |
| **E2E** | Playwright | 15 | ✅ Passed | Zero UI Regressions |
| **Load (Perf)** | k6 | 5,000 reqs | ✅ Passed | p95 Latency: 42ms (Budget: <100ms) |
| **Chaos** | Fault Injection | 4 Scenarios | ✅ Passed | DB Failover Recovered in 1.2s |
| **Fuzzing** | Fast-Check | 10,000 runs | ✅ Passed | 0 Uncaught Exceptions |
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.
- 2d ago First seen · 50 lines · 31 tokens per session scan A a7eb7c21b47f
sdlc-test is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 31 tokens to every session and 614 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
create-backend-tests
Command "create-backend-tests" from codeready-toolchain/tarsy, covering writing tests for go backend, running tests, from project root, direct go commands and critical rules.
perform-e2e-test
Execute end-to-end tests based on the E2E test plan and generate detailed test result reports.
design-e2e-test
Execute the E2E test design workflow to create comprehensive end-to-end test specifications for the entire product.
sdlc-dev
Phase 3 — Development & Coding. Spawns 9 agents with 4 parallel groups: backend-engineer, frontend+mobile, database, fullstack-engineer.
sdlc-parallel
Run multiple agents in parallel across phases with shared context and collaboration.
sdlc-plan
Phase 1 planning — grill-me interview + 4 sequential agents (product-manager → business-analyst → software-architect → security-architect).