@polygraph/opencode-plugin 0.4.42 → 0.4.43
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -0
- package/package.json +1 -1
- package/skills/adversarial-review/SKILL.md +15 -0
package/README.md
CHANGED
|
@@ -38,6 +38,7 @@ It detects your AI agent — Claude Code, Codex, OpenCode, and more — and inst
|
|
|
38
38
|
## Skills
|
|
39
39
|
|
|
40
40
|
- **polygraph** — Comprehensive guidance for Polygraph sessions: shared context, repository graph visibility, PR/CI state, delegation, and session management
|
|
41
|
+
- **adversarial-review** — Second-opinion review of a session's work by independent reviewer agents, one per repo, running under a read-only `reviewer` role
|
|
41
42
|
- **await-polygraph-ci** — Wait for CI pipelines to settle across all repos in a session, investigate failures, and present fix options
|
|
42
43
|
- **get-latest-ci** — One-shot fetch of the latest CI pipeline execution for the current branch
|
|
43
44
|
- **session-debrief** — Analyze the raw logs of past Polygraph sessions and produce structured, rank-ordered debriefs for use in a different session
|
package/package.json
CHANGED
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: adversarial-review
|
|
3
|
+
description: Independent second-opinion review of a Polygraph session's work. USE WHEN user says "adversarial review", "review this session", or when the Polygraph CLI launches an agent with an instruction to load this skill.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Adversarial Review
|
|
8
|
+
|
|
9
|
+
1. **Pick the agent.** Ask whether Claude, Codex, or OpenCode should review — `claude`, `codex`, or `opencode` for `spawn_agent`'s `agent` parameter. Skip if the user already named one.
|
|
10
|
+
2. **Get the session description.**
|
|
11
|
+
3. **Get each repo's plan.** Ask each repo's agent to provide the plan.
|
|
12
|
+
4. **Delegate one reviewer per repo** in parallel, with `role: "reviewer"`. Pass the overall plan and that repo's plan, and ask it to review the code, identify issues, and return a summary. Do the delegation even for the "initiator" repo.
|
|
13
|
+
5. **Summarize.** Once every review is back, analyze them and present one summary to the user.
|
|
14
|
+
6. **Ask what next.** Address the feedback, upload the summary via `upload_artifact`, or continue with the session. Skip if the user already said.
|
|
15
|
+
7. If the user selects "address the feedback", pass each repo's feedback to the repo default agent (not the reviewer). The initiator should fix things itself without delegating.
|