verify-local

A six-stage local smoke test for the SOVA command-line tool and its related installation, synchronization, adapters, and dashboard. A smoke test is a quick check that the main parts of a system still work together.

In plain words
What is it for?
Use it to check command entry points, run SOVA's diagnostics, install it into a temporary project, verify generated files, and briefly test the dashboard.
Why use it?
It catches broken commands, missing installation files, failed setup checks, and dashboard startup problems before relying on the tool.

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/verify-local
Clone the repo
git clone --depth 1 https://github.com/xsovad06/sova

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00026 $0.01134
Opus 5 $0.00013 $0.00567
Sonnet 5 $0.00005 $0.00227
Haiku 4.5 $0.00003 $0.00113

Measured 2d ago against content hash 4955ef85c66f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verify-local scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$tmp/smoke-test"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf http://localhost:8111/api/overview > /dev/null 2>&1
.claude/commands/verify-local.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Local

Run a 6-phase smoke test to verify SOVA works end-to-end on this machine. Exercises real CLI commands, creates a temp project, checks adapter creation, and briefly starts the dashboard.

Context: $ARGUMENTS

Instructions

Phase 1: CLI Entrypoints

Verify the CLI loads and new subcommands are registered:

sova --help
sova --version
sova doctor --help
sova commands sync --help

All four must exit 0. If any fails, report which one and stop.

Phase 2: sova doctor

Run the doctor on the SOVA project itself:

sova doctor --project .

Expected: exit 0, all required checks pass (Python, git, gh, claude). Report the output table.

Phase 3: Fresh Project Install

Test the full install pipeline on a disposable temp project:

tmp=$(mktemp -d)
git init "$tmp/smoke-test"

Then run:

sova install "$tmp/smoke-test"

Verify these artifacts exist:

  • $tmp/smoke-test/sova.toml
  • $tmp/smoke-test/.claude/commands/ (non-empty)
  • $tmp/smoke-test/.claude/agent-memory/MEMORY.md
  • $tmp/smoke-test/.claude/sova.db

Run doctor on the new project:

sova doctor --project "$tmp/smoke-test"

Clean up:

rm -rf "$tmp/smoke-test"

Report PASS if all artifacts exist and install exits 0.

Phase 4: Command Sync

Test multi-project command synchronization:

sova commands sync

If registered projects exist: verify it reports per-project results and a summary line. If no projects registered: verify it prints the "no projects" message and exits 0. Report as PASS (expected on fresh machines).

Phase 5: Adapter Factory

Verify the adapter factory creates both adapter types correctly:

python3 -c "
from sova.config.models import ProjectConfig, TaskSourceConfig
from sova.adapters import create_adapter

# GitHub adapter
cfg = ProjectConfig(github_repo='test/repo', github_user='testuser')
a = create_adapter(cfg)
assert a.__class__.__name__ == 'GitHubAdapter', f'Expected GitHubAdapter, got {a.__class__.__name__}'
assert a.github_user == 'testuser'
print('  GitHub adapter: OK')

# Jira adapter
cfg = ProjectConfig(task_source=TaskSourceConfig(
    type='jira',
    jira_base_url='https://test.atlassian.net',
    jira_email='[email protected]',
    jira_api_token='test-token',
    jira_project_key='TEST',
))
a = create_adapter(cfg)
assert a.__class__.__name__ == 'JiraAdapter', f'Expected JiraAdapter, got {a.__class__.__name__}'
assert a.project_key == 'TEST'
print('  Jira adapter: OK')

# Unknown type raises ValueError
try:
    ts = TaskSourceConfig()
    ts.type = 'unknown'
    create_adapter(ProjectConfig(task_source=ts))
    assert False, 'Should have raised ValueError'
except ValueError as e:
    assert 'Unknown adapter type' in str(e)
    print('  Unknown type rejection: OK')

print('  All adapter checks passed')
"

Read the full file on GitHub · 174 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 · 174 lines · 26 tokens per session scan C 4955ef85c66f

Subscribe to this mod's changes

verify-local is a command published in the GitHub repository xsovad06/sova (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,134 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.