secondmate-verify

A command that checks a worktree before integration by examining its Git state, changes, commit identity, and tests.

In plain words
What is it for?
Use it as a pre-merge gate to verify a maker's worktree and report either PASS or the exact reasons for refusal.
Why use it?
It prevents merging work that has no usable changes, was checked at the wrong commit, has a dirty tree, or fails its tests.

Command

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/eshwarvijay/secondmate/secondmate-verify
Clone the repo
git clone --depth 1 https://github.com/eshwarvijay/secondmate
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 177 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 $0.00032 $0.00177
Opus 5 $0.00016 $0.00088
Sonnet 5 $0.00006 $0.00035
Haiku 4.5 $0.00003 $0.00018

Measured 2d ago against content hash 5b79b01c0ee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secondmate-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 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.

commands/secondmate-verify.md · 17 lines

What it actually says

Run the secondmate verify-gate and report PASS or the exact REFUSE reasons. Do NOT integrate/merge unless it PASSes.

Arguments (worktree path, base branch, and the SHA the checker reviewed): $ARGUMENTS

Execute (fill the values from the arguments; add --test "<cmd>" if a test command applies):

"${CLAUDE_PLUGIN_ROOT}/bin/verify-gate.sh" --worktree <worktree> --base <branch> --checked-sha <sha>

Passing --checked-sha (the exact commit the checker reviewed) is mandatory — it catches a maker pushing new commits after the checker approved.

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 · 17 lines · 32 tokens per session scan A 5b79b01c0ee5

Subscribe to this mod's changes

secondmate-verify is a command published in the GitHub repository eshwarvijay/secondmate (3 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 177 once invoked, about $0.0002 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.