skip to content

The summarize-review prompt

The whole text of config/agent-prompts/summarize-review.md, as an agent is handed it.

Bundled agent prompts — one row of 30, exported from config/agent-prompts · every prompt · the resolution order

What this prompt is

id summarize-review the key every tier, every pattern step and every override spells it by
kind not a stage instruction whether any bundled pattern hands it to an agent step
role the harness role the agent reading it runs under
stage the stage of a run it is handed at
bundled at config/agent-prompts/summarize-review.md where the built-in copy sits in Gantry's own tree

No bundled pattern hands this file to an agent step. That is one honest answer to three different questions — a template the engine wraps other instructions in, a standing brief for something that is not a pipeline stage, or a file that is not a prompt at all — so the row says what the code can be asked rather than inventing a role for it.

Where an override of it goes

tier the file to write what it is
run
consulted 1st
.gantry/<plan>/prompts/summarize-review.md the run's own frozen copy, written when the run started and read by every agent it launches; edit it to change what a run's remaining agents are told
project
consulted 2nd
.gantry/<plan>/summarize-review.md a per-run override an operator drops beside the run's other orchestration files
global
consulted 3rd
~/.config/gantry/agent-prompts/summarize-review.md the materialized global mirror; it overrides the built-in once its bytes differ from the built-in's
built-in
consulted 4th
config/agent-prompts/summarize-review.md the default compiled into the binary

The text

config/agent-prompts/summarize-review.md
You are summarizing a code review for a status dashboard card.

Below is the reviewing agent's output for a sprint, and the diff of any changes the review itself made to the tree. In **1–2 short plain sentences** (never more than ~220 characters total), say what the review found. Use proper sentence case, start with a capital letter, and do not return all-lowercase prose. When the review edited the tree, lead with **what it changed**; otherwise say it passed clean.

Review output:
{{REVIEW}}

What the review changed:
{{DIFF}}

Output only those sentences — no preamble, no markdown, no code fence, no line breaks.