opsx-verify

opsx-verify is a command for Claude Code from iolairus/borderlint. It costs 8 tokens per session (879 once invoked), scanned A, original, MIT.

A command that checks whether completed code matches its written change documents, such as specifications, task lists, and designs, before the change is archived.

In plain words
What is it for?
Use it to select an OpenSpec change, read its related documents, and verify the implementation against them.
Why use it?
It helps catch differences between what was planned and what was built before the records are closed.

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/iolairus/borderlint/opsx-verify
Clone the repo
git clone --depth 1 https://github.com/iolairus/borderlint

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.

agentmods badge for opsx-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/iolairus/borderlint/opsx-verify.svg)](https://agentmods.dev/commands/iolairus/borderlint/opsx-verify)
Your own site
<a href="https://agentmods.dev/commands/iolairus/borderlint/opsx-verify"><img src="https://agentmods.dev/badge/commands/iolairus/borderlint/opsx-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 879 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 $0.00008 $0.00879
Opus 5 $0.00004 $0.00439
Sonnet 5 $0.00002 $0.00176
Haiku 4.5 $0.00001 $0.00088

Measured 3d ago against content hash 612d53c7d835, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opsx-verify 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.

.claude/commands/opsx-verify.md · 112 lines

What it actually says

Verify that an implementation matches the change artifacts (specs, tasks, design) before archiving.

Input: Optionally specify a change name after /opsx-verify (e.g., /opsx-verify add-auth). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.

Steps

  1. Select the change

    If a name is provided, use it. Otherwise:

    • Infer from conversation context if the user mentioned a change
    • Auto-select if only one active change exists
    • If ambiguous, run openspec list --json to get available changes and use the AskUserQuestion tool to let the user select

    Always announce: "Verifying change: " and how to override.

  2. Check status to understand the schema

    openspec status --change "<name>" --json
    

    Parse the JSON to understand:

    • schemaName: The workflow being used
    • Which artifacts exist for this change
  3. Get the change directory and load artifacts

    openspec instructions apply --change "<name>" --json
    

    This returns contextFiles (artifact ID -> array of concrete file paths). Read all available artifacts from contextFiles.

  4. If the openspec-verify-change skill is available, load it for the full execution logic

    The skill provides the detailed verification procedure across three dimensions:

    • Completeness: Tasks done, spec coverage
    • Correctness: Requirements implemented, scenarios covered
    • Coherence: Design followed, pattern consistency

    Follow the skill's steps to perform the verification and generate the report.

  5. If the skill is not available, perform a basic verification

    • Read tasks file and check - [x] vs - [ ] completion
    • Read delta specs and search codebase for requirement coverage
    • Read design and check for obvious contradictory implementation
    • Report findings with CRITICAL / WARNING / SUGGESTION priority levels
  6. Generate and display the verification report

    Output the report with:

    • Summary scorecard (Completeness / Correctness / Coherence)
    • Issues grouped by priority (CRITICAL, WARNING, SUGGESTION)
    • Final assessment: ready for archive or issues to fix

Output On Success (All Clear)

## Verification Report: <change-name>

### Summary
| Dimension    | Status          |
|--------------|-----------------|
| Completeness | 6/6 tasks ✓     |
| Correctness  | 3/3 reqs ✓      |
| Coherence    | No issues ✓     |

### Final Assessment
All checks passed. Ready for archive.

Output On Success (With Issues)

## Verification Report: <change-name>

### Summary
| Dimension    | Status          |
|--------------|-----------------|
| Completeness | 4/6 tasks       |
| Correctness  | 2/3 reqs        |
| Coherence    | Issues found    |

### Issues

**CRITICAL** (Must fix before archive):
- [ ] 2 incomplete tasks: 1.3, 1.4
- [ ] 1 missing requirement: "User can export data"

**WARNING** (Should fix):
- Design decision not followed: Use SQLite (using Postgres instead)

**SUGGESTION** (Nice to fix):
- Code pattern deviation: file naming mismatch

### Final Assessment
2 critical issue(s) found. Fix before archiving.

Guardrails

  • Always read the change artifacts before verifying
  • If the openspec-verify-change skill exists, use it - it has richer verification logic
  • Be conservative: prefer SUGGESTION over WARNING, WARNING over CRITICAL when uncertain
  • Every issue must have a specific, actionable recommendation
  • If no artifacts exist to verify against, report that clearly
  • Gracefully degrade: if only tasks exist, verify tasks; if full artifacts exist, verify all dimensions
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. 3d ago First seen · 112 lines · 8 tokens per session scan A 612d53c7d835

Subscribe to this mod's changes

opsx-verify is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 11d ago), licensed MIT. It adds 8 tokens to every session and 879 once invoked, about $0.0000 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.