A command for creating a Technical Requirements Document (TRD), which explains how a feature should be built. It combines product requirements, Figma designs, the existing codebase, and optional backend or testing documents for mobile work.

Use it to prepare mobile feature requirements from Confluence pages, Figma designs, and code. It can also capture acceptance criteria, business rules, user flows, data details, tracking events, and exact text.

It turns scattered design and project information into one structured implementation document. This helps clarify requirements before coding begins.

How tomdwipo/claude-soul configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/trd.md

Clone the repo

git clone --depth 1 https://github.com/tomdwipo/claude-soul

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/tomdwipo/claude-soul/trd.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/trd)

Your own site

<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/trd"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/trd.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,862 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00000	$0.03862
Opus 5	$0.00000	$0.01931
Sonnet 5	$0.00000	$0.00772
Haiku 4.5	$0.00000	$0.00386

Measured 8d ago against content hash 501b6990e08a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

trd 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 8d 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.

.claude/commands/trd.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TRD Command (Phase 1: Pre-Implementation)

Generate a Technical Requirement Document for: $ARGUMENTS

This command produces a mobile-side TRD grounded in PRD + Figma (decoded) + codebase + (optional) BE TRD + QA TRD, following the 14-section structure proven across the 2026-05-25 batch (FDS V3 Biller / Account Opening Legality / HyperVerge POC).

Instructions

Step 1: Gather inputs

Primary inputs: PRD (Confluence) · Figma · existing codebase. NOT Jira (Jira is tracking, not requirements).

1a. PRD — Confluence (source of truth)

URL or page ID in $ARGUMENTS → mcp__atlassian__getConfluencePage (markdown contentFormat).
Feature name only → mcp__atlassian__searchConfluenceUsingCql then fetch.
Extract: requirements table, acceptance criteria, business rules, user flows, document/data tables, event-tracker spec, exact Indonesian copy.

1b. Figma — drill the flow, don't guess

Priority order:

Local .fig + fig-decode — check ~/Downloads/*.fig and ~/Downloads/fig-decoded/ (and $TMPDIR/fig-decode-* as fallback). If the file is available:
- Re-decode to a durable output: ~/.claude/skills/fig-decode/decode.sh "<path>" --out=~/Downloads/fig-decoded/<name> (per the gotchas catalog — $TMPDIR is wiped on reboot).
- For files >150 MB use NODE_OPTIONS="--max-old-space-size=6144".
- Drill the node-id from the Figma URL via ~/.claude/skills/fig-decode/scripts/find_node.py <node-id> --out=<decoded-dir>. URL form 12894-95543 and colon form 12894:95543 both work.
- Extract child SECTION/FRAME names, decision-diamond text labels, connector labels (Yes/No/Already-Exist/Service-Error).
- Record re-drillable node IDs in the TRD appendix for future maintenance.
mcp__figma__get_file_nodes as fallback when no local .fig exists.
User-provided screenshot as last resort.

1c. BE TRD — only if explicitly supplied

--be-trd <url> or BE TRD page id → fetch with getConfluencePage.
If BE TRD is empty stubs (Enum/REST tables blank) — flag explicitly in §6 and write the mobile-recommended proposal as the BE contract (extend-first, see §6 pattern below).
If no BE TRD link is given, search the Confluence space for parent = <feature-PRD-parent> and confirm with the user before proceeding.

Read the full file on GitHub · 304 lines

Changes

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.

8d ago First seen · 304 lines · 0 tokens per session scan A 501b6990e08a

Subscribe to this mod's changes

trd is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,862 tokens. 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 2026-08-30.

Planning Writing and docs

claude-soul: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

TRD Command (Phase 1: Pre-Implementation)

Instructions

Step 1: Gather inputs

1a. PRD — Confluence (source of truth)

1b. Figma — drill the flow, don't guess

1c. BE TRD — only if explicitly supplied

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze