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-buildgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWrote 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/commands/saitarrun/devforge-ai/sdlc-build)<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/sdlc-build"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/sdlc-build.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.02158 |
| Opus 5 | $0.00025 | $0.01079 |
| Sonnet 5 | $0.00010 | $0.00432 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
sdlc-build 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 3d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-build — Phase 2: Build
Implements the feature slice-by-slice using the tracer bullet pattern. Each slice is a vertical cut through all required layers (schema → API → UI → tests), verified before the next begins.
Agents Invoked
ux-designer— once before the slice loop (only whenhas_ui: true)fullstack-engineer— once per slice (Slice 0 + all feature slices)qa-engineer— once after all slices complete- Ralph Loop skill applied at each fullstack-engineer invocation
STEP 1: Read Handoff (Clean Context Window)
Read ./projects/<feature>/handoffs/plan-handoff.md before doing anything else.
This document contains the distilled context from the Plan phase — grill-summary decisions, scope.json snapshot, and the slice decomposition. Loading it first ensures the Build phase starts with a bounded, fresh context window rather than carrying the entire Plan conversation forward.
STEP 2: Read scope.json
Read ./projects/<feature>/scope.json to extract:
capability_flags.has_ui— controls whether ux-designer runscapability_flags.has_auth,has_mobile,has_data_pipeline— inform fullstack-engineer contextslices[]— the ordered build plan:[{id, name, type, layers, linear_id?}]
The first slice is always "type": "prefactor". All subsequent slices are "type": "feature".
STEP 3: UX Design (scope-gated on has_ui)
If has_ui: true:
Invoke ux-designer once before any slice begins:
Agent: ux-designer
Context:
- ./projects/<feature>/grill-summary.md
- ./projects/<feature>/scope.json (full slices list)
- ./projects/<feature>/handoffs/plan-handoff.md
Output: ./projects/<feature>/docs/ux-design.md
- Wireframes for all UI slices
- Component specs and design tokens
- User flow diagrams
- Interaction states (loading, error, empty, success)
ux-designer runs exactly once — not per slice. All subsequent fullstack-engineer invocations reference ux-design.md.
If has_ui: false: Skip ux-designer entirely. No invocation, no artifact.
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.
- 3d ago First seen · 258 lines · 50 tokens per session scan A fdb07f04adf8
sdlc-build is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,158 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 2026-08-31.
Other commands, from other repositories
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
design-chatbot
Design a complete chatbot or conversational assistant UI — dialog flows, message bubbles, quick replies, typing indicators, error states, and accessibility.
figma
Convert a Figma design to production code. Provide a Figma URL or select a node in Figma desktop.
motion-design
Design micro-interactions, transitions, and animation systems for UI components or full pages.
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.
interaction-designer
Use when deciding how something should behave rather than how it looks. Click and tap targets, gestures, keyboard paths, loading and empty and error states, and the feedback each action gives.