Borrowing it
Nothing to install: this file belongs to paulieb89/uk-due-diligence-mcp. 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/paulieb89/uk-due-diligence-mcp/main/.claude/commands/verify.mdgit clone --depth 1 https://github.com/paulieb89/uk-due-diligence-mcpWrote 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/paulieb89/uk-due-diligence-mcp/verify)<a href="https://agentmods.dev/commands/paulieb89/uk-due-diligence-mcp/verify"><img src="https://agentmods.dev/badge/commands/paulieb89/uk-due-diligence-mcp/verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/paulieb89/uk-due-diligence-mcp/verify"><img src="https://agentmods.dev/badge/commands/paulieb89/uk-due-diligence-mcp/verify.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.00588 |
| Opus 5 | $0.00010 | $0.00294 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
verify scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. `curl https://uk-due-diligence-mcp.fly.dev/health` — is the app up at all? What it actually says
/verify
Two checks, local first — it is instant and catches the thing that has actually shipped broken twice.
1. Repo invariants at rest
uv run --no-sync python .claude/hooks/check_invariants.py --standalone
Same script as the PostToolUse hook, same four checks, no payload. The hook
path only sees agent edits through Write|Edit|MultiEdit; a sed -i from Bash,
a human in vim, or a merge commit bypasses it, so this is the only thing that
asserts the version triad at rest. Exit 0 clean, exit 2 with the reason on
stderr — report that reason verbatim, do not paraphrase it.
The triad (pyproject.toml, server.py server card, server.json x2) is the
one that drifted at daaa9dc and again at v1.3.0. The same line runs in CI, in
deploy-staging.yml on every push to main and in release.yml before publish.
It fails open by design: anything it cannot parse is not an opinion. A clean exit therefore means "found no disagreement", not "verified every file".
2. Deployed smoke test
Run the deployed smoke test:
uv run --no-sync python scripts/mcp_smoke_test.py --deployed
It calls company_search(query="Carillion", items_per_page=2) against
https://uk-due-diligence-mcp.fly.dev/mcp and asserts total_results > 0
and that company 03782379 (CARILLION PLC) is present.
Report the result verbatim — the target, timing, total_results, the company
numbers returned, and PASS/FAIL. Exit 0 is pass, exit 1 is fail.
If it fails, do not guess at the cause. Check in this order and say which one broke:
curl https://uk-due-diligence-mcp.fly.dev/health— is the app up at all?scripts/check-deploy-drift.sh— is prod running the latest release tag?- A
CH_API_KEYproblem shows up as a tool error, not an empty result set.
An empty result set is a real regression, not a flaky test: Carillion is in liquidation, so its record is finished changing.
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.
- 3d ago First seen · 53 lines · 21 tokens per session scan A 7cd91192c979
verify is a command published in the GitHub repository paulieb89/uk-due-diligence-mcp (3 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 588 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
test-tdd
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
ui-aqa-flow-code-analysis
Phase 3 Code Analysis of ui-aqa-flow.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
plan-refactor
Plan a refactor as a sequence of safe verified steps, with tests established before anything moves.
prompt-optimization
Improve an underperforming prompt through structured changes measured against fixed cases.