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 agentmods add agents/watt-mind/factory/merge-verifygit clone --depth 1 https://github.com/watt-mind/factoryWrote 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/agents/watt-mind/factory/merge-verify)<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>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 | $0.00000 | $0.00288 |
| Opus 5 | $0.00000 | $0.00144 |
| Sonnet 5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
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.
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
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.
- 4d ago First seen · 26 lines · 0 tokens per session scan A 639cabb93ba9
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.
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.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
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…
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.
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.
ap-re-anchor
L4 terminal leaf - RE-ANCHOR. Confirms mission and roadmap frontier alignment after resume or compaction using the three-file governance state.