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-helpgit 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 | $0.00022 | $0.00761 |
| Opus 5 | $0.00011 | $0.00380 |
| Sonnet 5 | $0.00004 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
sdlc-help 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevForge AI Interactive Guide & Command Navigator
Welcome to DevForge AI! This command helps you navigate the entire toolkit with zero confusion.
🧭 What are you trying to accomplish?
Select the scenario that matches your goal:
1. 🚀 Build a New Startup or SaaS Feature (0 to 1)
/sdlc-startup "Idea description" # Scaffold MVP, Stripe monetization, PostHog telemetry & metrics
/sdlc-plan "Feature description" # Structured interview (grill-me) -> PRD -> Tracer slices -> Linear issues
/sdlc "Feature description" # Run the complete 5-Phase SDLC pipeline end-to-end
2. 🗺️ Explore & Navigate a Large Codebase (Up to 1.5M Files)
/sdlc-navigate "AuthService" # Trace symbol callers, callees, and dependencies
/sdlc-navigate src/billing/ --deep # Map module boundaries, imports, and coupling
/sdlc-navigate "payInvoice" --impact # Show what breaks if you modify this function
3. 🔍 Debug & Fix Complex Bugs (Root Cause Analysis)
/sdlc-diagnose "500 error on checkout" # Funnel 1.5M files -> find root cause -> surgical fix
/sdlc-implement "Fix issue #42" # Implement fix with self-correcting Ralph Loop
4. 🛡️ Security, CVEs, & Hardening
/sdlc-security --audit-only # SAST, dependency CVE scan & OWASP Top 10 report
/sdlc-security --fix-cves # Automatically patch vulnerable dependencies
/sdlc-security --protocol zero-trust # Implement mTLS and strict auth policies
5. 🏛️ Modernize Legacy Code & Monoliths
/sdlc-modernize "legacy_engine.c" --snapshot-tests # Golden Master characterization test suite
/sdlc-modernize src/monolith/ --pattern strangler # Strangler Fig proxy & microservice slice
6. 🧪 Run Multi-Tier Test Suites
/sdlc-test --suite unit # Fast pure business logic tests
/sdlc-test --suite integration # Testcontainers (Postgres, Redis, Kafka)
/sdlc-test --suite contract # Pact / OpenAPI consumer contracts
/sdlc-test --suite e2e # Playwright browser journeys
/sdlc-test --suite perf # k6 load & concurrency benchmarks
/sdlc-test --suite chaos # Fault-injection & resilience simulations
/sdlc-test --suite all # Full enterprise verification matrix
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 · 82 lines · 22 tokens per session scan A 0469cda504b9
sdlc-help is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 22 tokens to every session and 761 once invoked, about $0.0001 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
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).
agent-farm
The afx (agent-farm) command manages multi-agent orchestration for software development. It spawns and manages builders in isolated git worktrees.
overview
Codev provides three CLI tools for AI-assisted software development.
consult
The consult command provides a unified interface for AI consultation with external models (Gemini, Codex, Claude, Hermes). It operates in three modes: general (ad-hoc prompts), protocol-based (structured reviews), and stats.