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/to-prdgit 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/to-prd)<a href="https://agentmods.dev/commands/saitarrun/devforge-ai/to-prd"><img src="https://agentmods.dev/badge/commands/saitarrun/devforge-ai/to-prd.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 | $0.00041 | $0.00874 |
| Opus 5 | $0.00020 | $0.00437 |
| Sonnet 5 | $0.00008 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
to-prd 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/to-prd — Synthesize PRD from grill-summary + scope.json
Reads ./projects/<feature-name>/grill-summary.md and ./projects/<feature-name>/scope.json and writes ./projects/<feature-name>/docs/01-prd.md.
Usage
/to-prd "login-page"
/to-prd "reporting-dashboard"
The <feature-name> must match the directory under ./projects/.
EXECUTION
STEP 1: Read artifacts
- Read
./projects/<feature-name>/grill-summary.md - Read
./projects/<feature-name>/scope.json
If either file is missing, halt and tell the user:
❌ Missing required files:
- grill-summary.md: [found/not found]
- scope.json: [found/not found]
Run /sdlc-plan first to generate these files, or provide them manually.
STEP 2: Synthesize PRD
Create ./projects/<feature-name>/docs/01-prd.md:
# PRD — [Feature Name]
**Date**: [today's date]
**Status**: Draft
## Problem Statement
[From grill-summary: what problem is being solved, why it matters now, prior attempts, underlying assumption]
## Users & Personas
[From grill-summary: each persona with their role, pain point, current workaround, success metric]
## Constraints
### Timeline
[From grill-summary: target ship date, why that date, realism assessment]
### Budget & Team
[From grill-summary: engineering capacity, estimated effort, trade-offs if over budget]
### Technical Constraints
[From grill-summary: must-integrate systems, prohibited tech, preferred stack]
### Compliance & Security
[From grill-summary: regulatory requirements, security concerns]
## Success Criteria (QUANTS)
| Dimension | Target |
|-----------|--------|
| Quality | [uptime %, error rate, bug tolerance] |
| Attention | [eng time allocation] |
| Toil | [manual work eliminated] |
| Time | [deployment frequency, lead time] |
| Satisfaction | [NPS/CSAT target, adoption %] |
## Capability Flags
| Flag | Value |
|------|-------|
| has_ui | [true/false] |
| has_auth | [true/false] |
| has_mobile | [true/false] |
| needs_pentest | [true/false] |
| has_data_pipeline | [true/false] |
| needs_performance_audit | [true/false] |
## Slices
| ID | Name | Type | Layers |
|----|------|------|--------|
[one row per slice from scope.json]
## Decisions Made
[From grill-summary: key decisions reached during interview]
## Open Questions
[From grill-summary: anything still unresolved]
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 · 139 lines · 41 tokens per session scan A 608e5ecdf8c8
to-prd is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 41 tokens to every session and 874 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
feature-plan
Guide the agent to create or update a feature plan from a short feature request.
ghost-decode
Decode a ghost-font video and reveal the hidden text.
video
description: Generate a video with Modellix from a prompt, an image, or a source video. argument-hint: [prompt] [optional image or video URL] disable-model-invocation: true.
doctor
Check the Modellix CLI install, credential resolution, API connectivity, and balance.
models
Find Modellix models and their request-body schema before running a task.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.