audit-alignment

A project consistency check across GitHub Issues, a project board, a vision document, and the actual code. It looks for differences between what the project says and what has been built.

In plain words
What is it for?
Use it to review open and closed issues, compare milestones and vision statements with implementation, and identify naming or status inconsistencies.
Why use it?
It helps find stale tasks, outdated milestones, and documentation that no longer matches the code. This reduces confusion about the project's real status.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/xsovad06/sova/audit-alignment
Clone the repo
git clone --depth 1 https://github.com/xsovad06/sova

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01707
Opus 5 $0.00012 $0.00853
Sonnet 5 $0.00005 $0.00341
Haiku 4.5 $0.00002 $0.00171

Measured 2d ago against content hash fd2527922dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-alignment 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.

.claude/commands/audit-alignment.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Alignment Audit

Verify that the project board, issue tracker, vision document, and codebase are consistent and up to date.

Focus area: $ARGUMENTS

Role

You are a project manager auditing the SOVA project for consistency across its planning artifacts (GitHub Issues, project board, VISION.md) and actual implementation state. Your job is to find drift: issues that are done but open, milestones that should be closed, vision sections that describe planned features as if they don't exist yet when they do, stale naming ("PAK" instead of "SOVA"), and any other inconsistencies.

Be thorough and specific. Every finding must reference a concrete issue number, milestone name, file path, or line range.

Phase 1: Gather State

Run all of these in parallel to build a complete picture.

1a. GitHub Issues

gh issue list --state all --limit 100 --json number,title,state,labels,milestone,createdAt,closedAt,body

Extract:

  • All open issues: number, title, labels, milestone, age (days since creation)
  • All closed issues with status: superseded label (just count them)
  • Any closed issue that references "PAK" in title or body

1b. Project Board

gh api graphql -f query='query { user(login:"xsovad06") { projectV2(number:2) { items(first:50) { nodes { content { ... on Issue { number title state } } order: fieldValueByName(name:"Priority Order") { ... on ProjectV2ItemFieldNumberValue { number } } phase: fieldValueByName(name:"Phase") { ... on ProjectV2ItemFieldSingleSelectValue { name } } status: fieldValueByName(name:"Status") { ... on ProjectV2ItemFieldSingleSelectValue { name } } } } } } }'

Extract:

  • Board items where issue is CLOSED but board status is not "Done"
  • Board items where issue is OPEN but board status is "Done"
  • Items with no Priority Order assigned
  • Phase distribution (count per phase)

1c. Milestones

gh api repos/xsovad06/sova/milestones --jq '.[] | {title, state, open_issues, closed_issues}'

Read the full file on GitHub · 207 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.

  1. 2d ago First seen · 207 lines · 23 tokens per session scan A fd2527922dd8

Subscribe to this mod's changes

audit-alignment is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,707 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.