Skip to content
Agentmart
Submit a tool

comptext-pr-review-memory

Preserve compact PR review memory for dry-run CompText token-saving workflows.

Skill by ProfRandom92

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying comptext-pr-review-memory?

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.

Book a call

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/profrandom92-comptext-pr-review-memory-f86658

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.

We use your email only for this newsletter. Privacy

About

Preserve compact PR review memory for dry-run CompText token-saving workflows.

No 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
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/comptext-pr-review-memory

What's inside

Skill name
comptext-pr-review-memory
Description
Preserve compact PR review memory for dry-run CompText token-saving workflows.
License
Apache-2.0
Instructions
78 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: "comptext-pr-review-memory" does not match folder "pr-review-memory"

Files (9)

  • README.md
  • SKILL.md
  • pr-review-input.sample.json · examples/
  • pr-review-memory.sample.json · examples/
  • token-saver-handoff.sample.md · examples/
  • plugin.json
  • renderer.py
  • README.md · schema/
  • pr-review-memory.v0.schema.json · schema/

SKILL.md (first lines)

# CompText PR Review Memory

## Purpose

Use this skill to emit compact PR review memory blocks for recurring review workflows. The output is meant to be consumed by token-saving context workflows, including CompText Token Saver when available, without duplicating that plugin.

For local autonomous Codex batches, also follow `docs/CODEX_LOCAL_AUTONOMY.md`.

## When to use

- Before long PR review work, summarize the current review state.
- After fixing review comments, summarize what changed and what remains.
- Before merge-readiness checks, preserve known blockers and validation status.
- Before preparing the next task prompt, create a compact handoff block.

## Inputs

- Repository name.
- PR number or local PR identifier.
- Branch, base branch, and head SHA when known.
- Review threads and thread state.
- Actionable comments and decisions.
- File paths touched by fixes.
- Validation commands and results.
- Mergeability or merge-readiness evidence.

## Outputs

- PR review memory summary.
- Gemini or reviewer comment summary.
- Merge-readiness summary.
- Token Saver handoff block.
- Deterministic local renderer v0 output from `plugins/pr-review-memory/renderer.py` when structured review-memory JSON is available.
- Renderer input schema v0 contract from `plugins/pr-review-memory/schema/pr-review-memory.v0.schema.json`.

Keep output compact. Preserve only decisions, blockers, file paths, thread state, validation, and next action.

## Required checks

- Summarize review state before long work.
- Confirm whether review threads are resolved, unresolved, or out of scope.
- Confirm validation status with concrete commands or note that validation was not run.
- Confirm merge readiness only after checking the current branch, base, and review state.
- Use `render_pr_review_memory_handoff(data)` for local conversion when the review memory is already structured as a dictionary.
- Keep structured renderer input aligned with the v0 schema contract and add compatibility tests before changing required fields.
- Keep provider states and external integrations limited to documented dry-run behavior.

## Safety notes

- No network calls.
- No GitHub API calls.
- No provider calls.
- No environment-variable reads.
- No secrets, API keys, raw provider payloads, or hidden chain-of-thought.
- No MCP runtime server behavior.
- No automatic PR modification.
- No merge behavior.
- No live GitHub integration or automatic review-thread resolution.

## Anti-patterns

- Do not duplicate full diffs unless a narrow excerpt is needed to understand a blocker.
- Do not dump full review transcripts when a compact decision summary is enough.
- Do not mark unresolved work as resolved.
- Do not claim mergeability without checking.
- Do not assume CompText Token Saver is installed.
- Do not present this scaffold as production-ready.
- Do not treat renderer output as proof that review threads are resolved or that a PR is mergeable.

## Related docs

- [Plugin README](README.md)
- [Codex Local Autonomy](../../docs/CODEX_LOCAL_AUTONOMY.md)
- [CompText Plugin System](../../docs/PLUGIN_SYSTEM.md)
- [CompText Context and Memory](../../docs/CONTEXT_AND_MEMORY.md)
- [Codex Desktop Workflow](../../docs/CODEX_DESKTOP_WORKFLOW.md)

From ProfRandom92/Comptext, Apache-2.0.

More from ProfRandom92/Comptext

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 21, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ProfRandom92

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 comptext-pr-review-memory 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying comptext-pr-review-memory?

CallGet help
Cite this page

comptext-pr-review-memory skill. Agent Mart. https://agentmart.dev/skills/profrandom92-comptext-pr-review-memory-f86658 (last updated 2026-10-24)