One-shot read-only review of a GitHub PR: dispatches the `pr-reviewer` agent once and reports its verdict and findings without touching your code. Also writes maintainer relevance rules via `/pr-review remember <fact>`; invoke with /pr-review.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Dispatch the pr-reviewer agent at a PR and report what came back.
It never applies a finding, never pushes, and never resolves a thread.
Why each choice below exists: references/design-rationale.md.
Parse the first token of $ARGUMENTS.
| First token | Operation | Runs |
|---|---|---|
remember | memory write — read rules/remember.md | one mcp__lorekit__memory_write, no review |
| anything else (or empty) | review | one pr-reviewer dispatch, read-only |
No mode turns this command into an apply pass; a request to fix findings is review-loop or /implement-suggestion (which command). Inside review-loop, --no-feedback is this command's report-only counterpart.
Agent0 cannot dispatch the custom pr-reviewer type, and its import can hold this SKILL.md alone.
Settle this before Step 0 and before any dispatch, by file presence and never from a failed dispatch.
It governs the review operation; remember dispatches nothing and resolves its tree on its own.
/tmp/workspace/agent-skills/env.sh exists. Source it (. /tmp/workspace/agent-skills/env.sh) in every Bash call; it exports AGENT_SUPPORT, AGENT_SKILLS_ROOT, and AGENT_SKILLS_COMMIT.
Read linked files from the install, never from the imported folder: this skill's rules/ and references/ from $AGENT_SKILLS_ROOT/skills/pr-review/, a sibling skill from $AGENT_SKILLS_ROOT/skills/<name>/, and every agents/<path> link from $AGENT_SKILLS_ROOT/<path>.
When $AGENT_SKILLS_ROOT/skills/pr-review/SKILL.md differs from the copy you are running, or you cannot compare them, follow the installed copy: the installed copy at $AGENT_SKILLS_COMMIT wins, because the files it links come from that commit.
Then make the dispatch substitutions in $AGENT_SKILLS_ROOT/shared/rules/agent0-host.md: pr-reviewer becomes a general sub-agent that reads $AGENT_SKILLS_ROOT/pr-reviewer.agent0.md, and the intent worker's type is general.env.sh, but /tmp/workspace, /tmp/.opencode/skills/, or /tmp/.opencode/agents/general.md exists. This skill does not install. Stop with /pr-review — skipped (Agent0 sandbox not prepared; run /review-loop <PR> --no-feedback, which installs on demand and reviews once). After that install, /pr-review takes the prepared branch.Everything after the PR reference is a pass-through flag: forward it verbatim and interpret none of it.
# Known agent flags, listed for the argument-hint only — NOT a validation allowlist.
# --critical --full --depth deep --model sonnet --with a,b,c --no-holistic --no-escalate
# --no-standards --skip-gates --fix-linksNever validate the flag list. Let the agent reject what it does not know.
case "$ARGUMENTS" in
*github.com/*/pull/*|*\#[0-9]*) PR_REF="<the reference as given>" ;;
*) PR_REF=$(gh pr view --json url -q .url 2>/dev/null) ;; # current branch's open PR
esacIf no reference was given and the current branch has no open PR, stop with one line:
/pr-review: no PR reference given and no open PR on this branch. Pass a URL or #<n>, or open a draft PR first (/create-pr).pr-reviewer has no PR-less mode.
Where gh is unavailable, resolve the reference with mcp__github__pull_request_read instead; a missing gh is never a reason to skip the review.
pr-reviewer is an agent, not a skill.
✅ RIGHT — through the harness's sub-agent dispatch tool
Task(subagent_type="pr-reviewer", prompt="<PR_REF> <pass-through flags>")
❌ WRONG — there is no skill by that name; this errors with `Unknown skill: pr-reviewer`
Skill("pr-reviewer", …)The dispatch tool is named Task in the Claude Code CLI and Agent in the Claude Agent SDK harness behind Claude Code on the web; use whichever this session exposes — any tool taking a subagent_type parameter is it.
Dispatch once; iterating against fixes is review-loop's job.
Prepare once, then send the intent worker in the same message when the budget says hybrid.
Settle dispatch availability first: a skip must not
leave a prepared workspace behind.
Pick a run directory, <scratchRoot()>/review-<PR number>-<unix seconds>/, and create it.
Resolve $AGENT_SUPPORT per Locating the support tree.
Read the PR-state record exactly as the agent's Step 0.7 does — mcp__lorekit__memory_read,
scope branch::<owner>/<repo>::<headRefName>, key ci-state::pr-review-<n> — and save a hit to
<dir>/state.json. Skip it under --isolated; on a miss, or with no LoreKit tool, pass no --state.
Run prepare once, forwarding only the pass-through flags it takes (--full, --effort,
--depth, --thoroughness, --finder-passes, --impact-image, --with, --isolated, --pin-head, --repo-dir; add --review-sha <sha> --isolated
when the pass-through flags carry --review-sha), and read the topology on the same command.
Never forward --model: it is a dispatch setting this skill applies in step 4, and prepare exits 2 on an argument it does not know.
A bad flag or flag combination exits 2 here, before any model turn: report prepare's message and stop.
node "$AGENT_SUPPORT/pr-reviewer/scripts/prepare-review.mjs" --pr <PR_REF> --out <dir>/context.json [--state <dir>/state.json] <prepare flags> \
&& jq -r '.budget.topology' <dir>/context.json && node "$AGENT_SUPPORT/pr-reviewer/scripts/review-telemetry.mjs" dispatch --run-dir <dir> \
&& mkdir -p <dir>/intent && date +%s > <dir>/intent/dispatched_atWrite whole seconds (%s); BSD date has no %N.
When the repo asked for a second finder pass, stamp it too:
if [ "$(jq -r '.budget.finderPasses // 1' <dir>/context.json)" = 2 ]; then mkdir -p <dir>/pass2 && date +%s > <dir>/pass2/dispatched_at; fiPick the models once ($AGENT_SUPPORT/pr-reviewer/rules/arguments.md, § The model axis):
--model when given, else none (the agent's own model: opus);jq -r '.reviewConfig.models.workers // empty' <dir>/context.json, else none.Pass a chosen model as the dispatch tool's model parameter on that dispatch only.
When the dispatch tool has no model parameter, dispatch without one and print models: not applied (<role>) under the report's run line; never invent another mechanism.
On hybrid, in one message, dispatch both:
pr-reviewer with <PR_REF> <pass-through flags> --context <dir>/context.json --intent-from <dir>/intent/intent.json,
then a new line INTENT_WAIT: followed by the wait command below with <dir> and $AGENT_SUPPORT already resolved to absolute paths.
The worker runs beside the reviewer, so the file does not exist when the reviewer starts; the reviewer runs this line at its Step 2.6b, after verifying its own candidates, replaces <N> with its own running tool-call count (the only part the caller cannot know), and never replaces the line with ls or cat:
node "$AGENT_SUPPORT/pr-reviewer/scripts/review-telemetry.mjs" step intent-wait --attr tool_calls_so_far=<N> --run-dir <dir>; node "$AGENT_SUPPORT/pr-reviewer/scripts/review-telemetry.mjs" worker intent import --from <dir>/intent --done <dir>/intent/intent.json --wait 540 --run-dir <dir>; cat <dir>/intent/intent.jsona general-purpose worker (the harness's general sub-agent type) with the worker preamble,
told to read <dir>/context.json, finders.md, and the review packet the context names, act as
the intent finder only, and write its candidates to <dir>/intent/intent.json as a JSON array.
It never runs prepare-review.mjs.
On in-context (the budget's topology, e.g. a lean quick routing or a small incremental re-review) — dispatch
pr-reviewer alone with --context <dir>/context.json, and no worker.
5b. When budget.finderPasses is 2, add two more general workers to the message from step 4 or 5,
whichever topology: both get the worker preamble and
<dir>/context.json, and neither runs prepare-review.mjs.
intent-2 acts as the intent finder only and writes <dir>/pass2/intent.json;other-finders-2 runs every other finder budget.finders turns on, from finders.md (plus
finder-consumer-impact.md and finder-dependency.md when those are on), and writes
<dir>/pass2/others.json.Pass the reviewer nothing extra: it finds <dir>/pass2/ beside its --context file and unions both
passes; finalize.mjs names any pass-2 unit that never delivered
(agents/pr-reviewer/rules/dispatch-topology.md § Two finder passes).
When every dispatch has returned, release the workspace: you ran prepare, so the cleanup is yours, never the reviewer's.
node "$AGENT_SUPPORT/pr-reviewer/scripts/prepare-review.mjs" --cleanup <dir>/context.jsonIf prepare exits non-zero, dispatch pr-reviewer alone with no --context: it runs prepare itself, owns that workspace's cleanup, and runs intent in-context.
The agent reads the intent file only after verifying its own candidates, and runs intent itself if the worker failed (dispatch-topology.md § The two topologies).
✅ RIGHT — prepare once, then one message, two dispatches
Task(subagent_type="general-purpose", prompt="<worker preamble> … read /…/context.json … act as the intent finder … write /…/intent/intent.json")
Task(subagent_type="pr-reviewer", prompt="<PR_REF> --context /…/context.json --intent-from /…/intent/intent.json\nINTENT_WAIT: node /…/review-telemetry.mjs step intent-wait --attr tool_calls_so_far=<N> --run-dir /…; node /…/review-telemetry.mjs worker intent import --from /…/intent --done /…/intent/intent.json --wait 540 --run-dir /…; cat /…/intent/intent.json")
❌ WRONG — no INTENT_WAIT line: a reviewer that runs `ls /…/intent` once sees an empty directory, reads it as "the worker failed", and finishes without the intent candidates
❌ WRONG — the worker in a second message: the reviewer's wait becomes the worker's full runtime
❌ WRONG — a worker told to run prepare-review.mjs: a second set of GitHub reads, and a leaked worktreeThe intent worker Step 2 dispatches gets this preamble prepended to its prompt, verbatim:
You are the intent worker for one pr-reviewer run, not the full pr-reviewer agent.
- Read ONLY the file(s) named below, by their ABSOLUTE path — never a bare relative path; your
cwd is not guaranteed to be this repo's checkout.
- Do NOT read agents/pr-reviewer.md. It is the full agent's own document; you are one finder of
its pipeline, dispatched with exactly the context that finder needs, and reading it would
re-derive context the dispatch already isolated you from (and burn the tokens doing it).
- Do NOT call Skill(). Read the rule file(s) you were given instead.
- Do NOT run prepare-review.mjs. The context file you were given is already prepared; read
context.packet.path from it.
- Read the review packet first (context.packet.path): the PR description and every hunk widened
against the head file, with head line numbers you cite directly. Open a workspace file only for
what it does not show — a caller, a definition, or a file its index marks "listed".
- Write your JSON output to the path you were given. Return ONLY that path in your final message
— never the payload inline. The reviewer reads the file from disk; a payload returned as text
spends context neither side needs to spend.Conclude this by capability — no available tool dispatches a sub-agent under any name — never from the absence of the name Task.
Then report the skip and stop:
/pr-review — skipped (sub-agent dispatch unavailable; pr-reviewer requires it).Do not play the reviewer role in this context, and do not retry the dispatch.
Where another process reviews the PR instead (a review bot, a CI-triggered agent), the supported path is /implement-suggestion <PR> --watch.
The agent posts its own sticky report comment and inline findings. This skill adds a terminal summary and nothing else — never a second GitHub write.
/pr-review on PR #<n> (<owner>/<repo>)
Verdict: <PASS | WARN | FAIL>
Run mode: <full | incremental | incremental-quick | zero-delta> · <deep | standard | quick> · <checkout | tarball | diff-only>
Findings: <N inline (<K> blocking)>, <D deferred (low-confidence, advisory)>
Gates: <one line naming any non-passing gate, or "all passing">
<one line per blocking finding: path:line — the ask>
Report: <URL of the sticky comment>
Apply these: /implement-suggestion <PR> (or Skill("review-loop", "<PR>") to converge)Surface blocking findings and non-passing gates prominently — this summary is the only place the result reaches the user.
Report the verdict as returned: never soften a FAIL or upgrade a PASS.
When a user asks how to give the reviewer knowledge of their repo, answer with this table; every row is read automatically, with no flag.
| The user wants the reviewer to… | They write | Read from |
|---|---|---|
| know architecture, invariants, or intent the code cannot show, for one part of the repo | REVIEW.md in that directory (the root one covers everything); the contract is agents/shared/rules/review-context.md | the PR's base commit |
| check a team's own checklist on its paths, from the next PR on | .agents/review/lenses/<name>.md (no registration; human guide: README.md) | the PR's base commit |
| enforce a written rule as a finding | a must/never line in CLAUDE.md, AGENTS.md, .claude/rules/*.md, or review-config standards: | the checkout; review config from the base |
| stop or start flagging one kind of finding | /pr-review remember <fact> or review-config filters: | relevance memory; the base |
<!-- ✓ services/query/REVIEW.md — a fact the code cannot show -->
- The query service reads only from replicas; ingest owns the primary, so any write here is a bug.
<!-- ✗ an instruction: REVIEW.md is context and never changes what the reviewer reports -->
- Don't comment on error handling in this folder.The scripts live in the pr-reviewer agent's support tree, not in the repository you are standing in, so a bare node agents/… exits MODULE_NOT_FOUND everywhere but this skill's own repository.
Resolve it in the same Bash call that uses it — Agent0 exports it from env.sh; elsewhere resolve it the way the agent does (its § Locating this agent's own files):
[ -f /tmp/workspace/agent-skills/env.sh ] && . /tmp/workspace/agent-skills/env.sh # Agent0: exports AGENT_SUPPORT
if [ -z "$AGENT_SUPPORT" ]; then
resolve() { # portable readlink -f
[ -e "$1" ] || return 1
( cd "$(dirname "$1")" && t=$(basename "$1")
while [ -L "$t" ]; do d=$(readlink "$t"); cd "$(dirname "$d")" || return 1; t=$(basename "$d"); done
printf '%s/%s\n' "$(pwd -P)" "$t" )
}
AGENT_MD=$(resolve "${CLAUDE_AGENT_FILE:-$HOME/.claude/agents/pr-reviewer.md}" \
|| resolve "$(agent-skills-root 2>/dev/null)/agents/pr-reviewer.md" || echo "") # plugin: bin/agent-skills-root
AGENT_SUPPORT="${AGENT_MD%/pr-reviewer.md}"
fihybrid, and the two pass-2 workers when budget.finderPasses is 2. Do not loop. The caller that ran prepare runs --cleanup.pr-reviewer review, and never retry the dispatch.PASS / WARN / FAIL as returned, with the blocking findings named.remember writes an fp-keyed rule with explicit: true, or asks — never an invented key — and never suppresses a standards or (blocking) finding (rules/remember.md).mthines/agent-skills
0ec47ca
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.