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.
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/prd-align.mdgit clone --depth 1 https://github.com/tomdwipo/claude-soulWrote 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/tomdwipo/claude-soul/prd-align)<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/prd-align"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/prd-align.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 5.1 | $0.00000 | $0.02980 |
| Opus 5 | $0.00000 | $0.01490 |
| Sonnet 5 | $0.00000 | $0.00596 |
| Haiku 4.5 | $0.00000 | $0.00298 |
Grade A, and why
prd-align 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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Alignment Tracker
Analyze, sync, and track PRD/TRD alignment with codebase: $ARGUMENTS
Instructions
Step 0: Mode Detection
Determine which mode to run based on $ARGUMENTS:
Rule 1 — CHECK mode: If $ARGUMENTS contains a Confluence URL, page ID, or feature name: → Go to Step 3 (CHECK mode)
Rule 2 — SYNC mode (forced):
If $ARGUMENTS contains --sync:
→ Go to Step 4 (SYNC mode)
Rule 3 — STATUS mode (forced):
If $ARGUMENTS contains --status:
→ Go to Step 5 (STATUS mode)
Rule 4 — Auto-detect (no arguments): If $ARGUMENTS is empty:
- Read
.docs/prd-registry/index.json - Get
lastSyncCommitvalue - Run
git rev-parse HEADto get current HEAD - If lastSyncCommit != HEAD → SYNC mode (Step 4)
- If lastSyncCommit == HEAD → STATUS mode (Step 5)
- If index.json doesn't exist → BOOTSTRAP (Step 1 first, then SYNC)
Step 1: Bootstrap Registry (First Run Only)
Only run if .docs/prd-registry/index.json does not exist.
- Create
.docs/prd-registry/directory - Create
index.jsonwith empty entries and tree configs:- cloudId: "your-org.atlassian.net"
- prdTrees: general (), lending (), cms ()
- trdTrees: lending (), funding ()
- Create
module-map.jsonwith empty object - Crawl each tree using
mcp__atlassian__confluence_get_page_children:- For each tree in prdTrees and trdTrees
- Paginate if needed (limit: 50)
- For each child page: create an entry with pageId, title, type (PRD/TRD based on tree), tree, parentId
- Set status: "UNSCANNED"
- Save all entries to
index.json - Log: "Bootstrap complete. {N} PRD/TRD entries indexed. Run /prd-align --sync to scan codebase."
- Proceed to SYNC mode (Step 4) automatically
Step 2: Entity Extraction (Shared Helper)
For a given Confluence page, extract alignment entities:
- Fetch page content using
mcp__atlassian__confluence_get_page(includeBody: true) - Extract from content:
- Screen names: Look for screen/page references (e.g., "Halaman KYC", "Upload Document Screen")
- API endpoints: Look for URL patterns, endpoint mentions (e.g.,
/api/v1/account-opening,POST /upload) - Data models: Look for entity/model names (e.g., "UBO data", "beneficiary", "account type")
- Feature flags: Look for remote config mentions (e.g.,
SHOW_CMS_FEATURE,SHOW_LOAN_FEATURE) - Business rules: Look for validation rules, conditions, limits
- Keywords: Extract top 10 domain-specific nouns for fuzzy matching
- Return extracted entities as structured data
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 · 283 lines · 0 tokens per session scan A 2320abfc0343
prd-align 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 2,980 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.