partner-reviewer
Run the bounded Partner Reviewer workflow for implementations that changed five or more unique files.
Skill by judepayne
Chalk Labs
Need help deploying partner-reviewer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/judepayne-partner-reviewer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/partner-reviewer
What's inside
- Skill name
partner-reviewer- Description
- Run the bounded Partner Reviewer workflow for implementations that changed five or more unique files.
- License
- MIT
- Instructions
- 65 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Partner Reviewer Workflow
Use this skill only when Builder's Partner Reviewer instruction applies. For that implementation packet, this workflow replaces the ordinary one-pass review policy.
## Trigger
Treat one user-requested implementation as one review packet.
Use Partner Reviewer when the current implementation changed five or more unique files. Determine this from the files changed during implementation; do not routinely run a separate counting command.
If the count is genuinely unclear at the final review decision point, you may verify it once. For example:
```bash
{ git diff --name-only --diff-filter=ACMRTUXB; git ls-files --others --exclude-standard; } | sort -u | wc -l
```
This command can include pre-existing user changes, so it is a fallback rather than the primary source of the count. Every implementation-touched path counts; do not exclude file types or reinterpret the threshold.
## Initial review
After implementation and focused validation are complete, launch one Partner Reviewer asynchronously:
```json
{
"agent": "partner-reviewer",
"task": "Perform the initial full review of the completed working-tree diff. Use the active design and plan as implementation intent, report findings by severity, and return an explicit clean, acceptable, or changes-required verdict.",
"context": "fresh",
"async": true,
"showRunCard": false
}
```
Include the concrete active design and plan paths in the task when they exist. Do not mutate reviewed files while the review is active. Follow the normal async handback rules: do not add a redundant launch acknowledgement, and answer using the completion result when it arrives.
Retain the latest returned `childSessionId` for this Partner Reviewer thread.
- `clean` or `acceptable`: close the review workflow.
- `changes-required`: address material findings, use judgment on Low findings, and run focused validation before closure review.
Do not also launch the ordinary `reviewer` for this packet.
## Closure review
Resume the same Partner Reviewer with one single-task asynchronous continuation:
```json
{
"agent": "partner-reviewer",
"task": "Perform the targeted closure review. Re-read the current diff, verify the remediation of every prior material finding, check for concrete remediation regressions, and return an explicit clean, acceptable, or changes-required verdict.",
"context": "continue",
"childSessionId": "<latest-child-session-id>",
"async": true,
"showRunCard": false
}
```
Use the concrete latest `childSessionId`; there is no implicit continue-latest operation. Do not mutate reviewed files while the closure review is active.
- `clean` or `acceptable`: close the thread.
- unresolved Critical/High findings: remediate, validate, and permit one final targeted continuation.
- other remaining findings after closure: report them and stop rather than looping.
Low findings never keep the review cycle open. The parent agent remains accountable for remediation choices, validation, and the final user response.From judepayne/picode, MIT.
More from judepayne/picode
- 0.587score
orchestrate-subagents
judepayne
Use mediated subagent delegation through delegate_subagent and delegate_subagent_status.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
prompt-vars
judepayne
Use prompt vars for the active plan and design files, plus merged project/global agent-mode vars.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
planning-workflow
judepayne
Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-designer
judepayne
Designer-mode automode handoff rules for explicit user-started Design → Plan → Build automation.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-planner
judepayne
Planner-mode automode rules for turning the active design into a Builder-ready plan and handing off to Builder.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
automode-builder
judepayne
Builder-mode automode rules for implementing the active plan and clearing automode on stop.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
pr-management
judepayne
Use the team-lead subagent to run a staged PR workflow.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
karpathy-coding-discipline
judepayne
Behavioral guidelines to reduce common LLM coding mistakes.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/judepayne/picode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from judepayne
- 0.587score
orchestrate-subagents
judepayne
Use mediated subagent delegation through delegate_subagent and delegate_subagent_status.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
prompt-vars
judepayne
Use prompt vars for the active plan and design files, plus merged project/global agent-mode vars.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
planning-workflow
judepayne
Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-designer
judepayne
Designer-mode automode handoff rules for explicit user-started Design → Plan → Build automation.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-planner
judepayne
Planner-mode automode rules for turning the active design into a Builder-ready plan and handing off to Builder.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
automode-builder
judepayne
Builder-mode automode rules for implementing the active plan and clearing automode on stop.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get partner-reviewer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
partner-reviewer skill. Agent Mart. https://agentmart.dev/skills/judepayne-partner-reviewer (last updated 2026-10-24)