merge-verify

merge-verify is an agent for coding agents from watt-mind/factory. It costs 0 tokens per session (288 once invoked), scanned A, original, Apache-2.0.

A deterministic gate for verifying that a batch of GitHub pull requests landed correctly and that the final commit passed required checks.

In plain words
What is it for?
It helps verify merged pull requests, poll checks on the final commit, run declared smoke tests, clean up merged worktrees and branches on success, and preserve them while blocking and notifying on failure.
Why use it?
It prevents branches from being deleted or tickets marked done when merge status or CI evidence is missing, stale, failed, or uncertain.

Agent

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 agents/watt-mind/factory/merge-verify
Clone the repo
git clone --depth 1 https://github.com/watt-mind/factory

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 merge-verify

README.md
[![agentmods](https://agentmods.dev/badge/agents/watt-mind/factory/merge-verify.svg)](https://agentmods.dev/agents/watt-mind/factory/merge-verify)
Your own site
<a href="https://agentmods.dev/agents/watt-mind/factory/merge-verify"><img src="https://agentmods.dev/badge/agents/watt-mind/factory/merge-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 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 $0.00000 $0.00288
Opus 5 $0.00000 $0.00144
Sonnet 5 $0.00000 $0.00058
Haiku 4.5 $0.00000 $0.00029

Measured 4d ago against content hash 639cabb93ba9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

merge-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 4d 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.

event-runtime/agents/merge-verify.md · 26 lines

What it actually says

merge-verify — exact batched landing gate

This is a deterministic command, not a model prompt. A durable factory.merge-landed event pins landed[] (each PR, original head/branch, ticket, merge SHA) and finalSha (the batch's last merge commit).

The command first proves GitHub still reports every landed PR as MERGED at its recorded merge SHA. It then polls with bounded deadlines for check-runs on finalSha only and, when the repo config declares smoke_workflow, that workflow on the same commit. Missing, red, cancelled, stale, or uncertain evidence fails closed.

Green: for every ticket in landed[], run the repo-owned worktree teardown for that ticket, verify the remote head branch still points at the merged head SHA, refuse protected branch names, delete exactly that ref, and mark the ticket Done. Then inject the next merge scan. Replays are idempotent at event admission.

Red: the existing CI/SMOKE RED handling runs for every ticket in landed[] (block + notify). Branches and worktrees are preserved. The merge barrier stays held. Apply never marks Done or deletes a branch.

bun {factoryRoot}/event-runtime/lib/merge-verify.mjs
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. 4d ago First seen · 26 lines · 0 tokens per session scan A 639cabb93ba9

Subscribe to this mod's changes

merge-verify is an agent published in the GitHub repository watt-mind/factory (10 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 288 tokens. 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.

Related

Other agents, from other repositories

ap-implementer

L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.

Spielewoy/autoprompt-skill · 52 tokens

ap-manager

L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.

Spielewoy/autoprompt-skill · 32 tokens

ap-framework-generator

L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…

Spielewoy/autoprompt-skill · 93 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ap-re-anchor

L4 terminal leaf - RE-ANCHOR. Confirms mission and roadmap frontier alignment after resume or compaction using the three-file governance state.

Spielewoy/autoprompt-skill · 33 tokens