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.
npx skills add spuentesp/lain --skill lain-verifygit clone --depth 1 https://github.com/spuentesp/lainWrote 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/skills/spuentesp/lain/lain-verify)<a href="https://agentmods.dev/skills/spuentesp/lain/lain-verify"><img src="https://agentmods.dev/badge/skills/spuentesp/lain/lain-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/skills/spuentesp/lain/lain-verify"><img src="https://agentmods.dev/badge/skills/spuentesp/lain/lain-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 | $0.00054 | $0.00453 |
| Opus 5.5 | $0.00022 | $0.00181 |
| Sonnet 5.5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
lain-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 19d 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.
What it actually says
Lain verify — ship-it checks
The verify package is not in the default surface because it
executes real processes (slow, side effects on disk/caches).
Load it when you actually intend to run something.
Load it
Call load_package("verify") — or set LAIN_TOOL_PROFILE=verify
at config time for agents that routinely verify. load_package
makes the tools appear in tools/list; tools are callable by
name even when hidden, but many MCP clients only permit tools
their cached list contains. If the tools do not appear after
loading, reconnect the client and refetch.
The tools
run_build/run_tests/run_clippy— the real thing: compile, run the suite (optionally filtered), lint (optionally auto-fix). Checkget_healthfirst so you are not testing a cold graph.find_untested_functions— where the call graph sees no test coverage. The right answer to "what should I test next".get_coverage_summary— structural estimate from connectivity. Fast, not a coverage report — say so when quoting it.get_test_template— a scaffold for one function or type.get_file_diff/get_commit_history/get_branch_status— git state before and after a change. For anything git-shaped beyond these, the shell is fine and often better.
Rules of thumb
- Never
run_build/run_testsjust to answer a question — read first (comprehension skill), verify after changing. - Long outputs: filter
run_testsrather than pulling the whole suite. - After a fix, the honest sequence is
assess_change→ edit →run_tests→get_file_diff.
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.
- 19d ago First seen · 43 lines · 54 tokens per session scan A 0270a3821ba6
lain-verify is a skill published in the GitHub repository spuentesp/lain (9 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 453 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
implement
Execute an approved phase plan with TDD, dependency-aware task fan-out, required evidence, and a strict iteration handoff.
validate-plan-testing
Plan testing validation gate - evaluates test strategy adequacy before implementation.
review-implementation-qa
Implementation review QA axis - live-runs the assembled feature for functional defects.
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.