merge-apply

merge-apply is an agent for coding agents from watt-mind/factory. It costs 0 tokens per session (332 once invoked), scanned A, original, Apache-2.0.

A controlled tool for applying a checked list of GitHub pull requests by squashing them into the develop branch. It rechecks each request immediately before merging.

In plain words
What is it for?
Use it to land approved pull requests in batches, record the exact resulting commit IDs, and request a fresh plan when none can be merged.
Why use it?
It prevents stale, blocked, failing, or no-longer-mergeable pull requests from being merged accidentally, while allowing other valid requests in the batch to continue.

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-apply
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-apply

README.md
[![agentmods](https://agentmods.dev/badge/agents/watt-mind/factory/merge-apply.svg)](https://agentmods.dev/agents/watt-mind/factory/merge-apply)
Your own site
<a href="https://agentmods.dev/agents/watt-mind/factory/merge-apply"><img src="https://agentmods.dev/badge/agents/watt-mind/factory/merge-apply.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 332 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 $0.00332
Opus 5 $0.00000 $0.00166
Sonnet 5 $0.00000 $0.00066
Haiku 4.5 $0.00000 $0.00033

Measured 3d ago against content hash 2dd21b7c8463, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

merge-apply 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 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.

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-apply.md · 26 lines

What it actually says

merge-apply — deterministic batched landing

This is a closed command definition, not a model prompt. Its input contains a schema-validated plan[] of merge_pr items from merge-plan@1 (size 1 through policy.merge.batch_size). Immediately before each squash, the command re-reads that PR's head and base SHA, exact branch names, open/draft/mergeable state, GitHub and Linear holds, and required CI. A stale, unmergeable, held, or red item is skipped with a reason; the rest of the batch continues. Only develop is auto-mergeable.

The command uses --match-head-commit, never deletes a branch, never tears down a worktree, and never marks Linear Done.

After GitHub proves each successful squash is MERGED, the command records that item's exact merge SHA. One idempotent factory.merge-landed event is emitted for the whole batch, carrying landed[] (pr, ticket, headSha, mergeSha, headRef) plus finalSha (the last successful merge SHA). That event is the only path to merge verification. If nothing landed, a refresh factory.merge.requested is emitted so skipped items can be re-planned. Uncertain merge (squash succeeded but SHA unreadable) fails the run when nothing has landed yet; after earlier successes it skips the remainder.

bun {factoryRoot}/event-runtime/lib/merge-apply.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. 3d ago First seen · 26 lines · 0 tokens per session scan A 2dd21b7c8463

Subscribe to this mod's changes

merge-apply is an agent published in the GitHub repository watt-mind/factory (10 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 332 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-feature-coordinator

L1 feature coordinator - drives approved ROADMAP.md lanes through their required build/review/verification gates and owns the run-wide feature frontier.

Spielewoy/autoprompt-skill · 33 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-framework-validator

L4 terminal leaf - FRAMEWORK VALIDATE (HRN-5). A fresh, default-FAIL juror that proves a GENERATED framework is SOUND before any gate runs. Checks the HRN-5 default-FAIL checklist - every gate mapped, exactly one terminal DONE with negatives looping UP, the BLOCKED invariant verbatim, a non-empty acceptance set. PASS…

Spielewoy/autoprompt-skill · 93 tokens

ap-scope-coordinator

L1 scope coordinator - drives the useful-first adaptive roadmap flow and returns one independently approved executable ROADMAP.md before build.

Spielewoy/autoprompt-skill · 30 tokens