pr-review-memory
Bridge Codex prompts to the dry-run PR Review Memory scaffold for compact Token Saver handoffs.
Skill by ProfRandom92
Chalk Labs
Need help deploying 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.
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-pr-review-memory
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: agent-building
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/pr-review-memory
What's inside
- Skill name
pr-review-memory- Description
- Bridge Codex prompts to the dry-run PR Review Memory scaffold for compact Token Saver handoffs.
- License
- Apache-2.0
- Instructions
- 62 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# PR Review Memory Use this repo-side Codex skill bridge with the personal Token Saver prompt header: `[@comptext-token-saver](plugin://comptext-token-saver@personal)` This bridge connects Codex instructions to the scaffold in `plugins/pr-review-memory/`. It can use deterministic local renderer v0 in `plugins/pr-review-memory/renderer.py` when structured review-memory JSON is already available, and the local schema contract in `plugins/pr-review-memory/schema/pr-review-memory.v0.schema.json` documents that input shape. It does not make provider calls, call GitHub APIs, write GitHub state, run an MCP server, resolve review threads, merge branches, or enable auto-merge. For local autonomous Codex batches, follow `docs/CODEX_LOCAL_AUTONOMY.md` and keep this bridge as compact instruction context. ## When to use - After PR creation. - When Gemini or review comments appear. - After actionable comments are fixed. - Before merge-readiness checks. - When preparing Token Saver handoff context. ## When not to use - Do not use this bridge to fetch review state, call GitHub APIs, resolve threads, push, merge, enable auto-merge, call providers, read secrets, or run MCP runtime behavior. - Do not use renderer output as proof of mergeability or review resolution. ## Compact handoff fields Preserve only the compact state needed to continue review work: - Repository. - PR number. - Branch. - Head SHA. - Review comments. - Fixes. - Validation. - Resolved and unresolved threads. - Merge readiness. - Next action. ## Output rules - Keep output compact. - Prefer decisions, blockers, file paths, validation results, head SHA, PR URL, and next action. - Avoid full diffs unless a narrow excerpt is required to explain a blocker. - Avoid secret values, raw environment variables, hidden chain-of-thought, and provider payloads. - Avoid unrelated file summaries. - Avoid broad repo scans. - Avoid automatic merge claims; only describe merge readiness after checking current state. - Do not claim production behavior. - Use renderer v0 only for local dictionary-to-markdown conversion; do not infer missing review state. - Keep renderer input aligned with schema v0 unless a task explicitly updates the contract and tests. ## Related scaffold files - `docs/CODEX_LOCAL_AUTONOMY.md` - `plugins/pr-review-memory/README.md` - `plugins/pr-review-memory/SKILL.md` - `plugins/pr-review-memory/plugin.json` - `plugins/pr-review-memory/renderer.py` - `plugins/pr-review-memory/schema/pr-review-memory.v0.schema.json` - `plugins/pr-review-memory/examples/token-saver-handoff.sample.md`
From ProfRandom92/Comptext, Apache-2.0.
More from ProfRandom92/Comptext
- 0.469score
ci-validation
ProfRandom92
Manage GitHub Actions validation workflows and Python compatibility.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-local-boundaries
ProfRandom92
Audit project doctor files and verify the containment boundaries.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-local-verify
ProfRandom92
Perform offline verify checks on status, subagents, workspace validation, and doctor diagnostics.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-pr-review-memory
ProfRandom92
Local checks and markdown rendering for pull request review summaries.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-status
ProfRandom92
View a summary of active workspace file presence and local diagnostics status.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-subagent-inventory
ProfRandom92
Inspect local subagent definitions, allowed file scopes, and routing matrix.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-workspace-validation
ProfRandom92
Validate workspace snapshot and delta files against JSON Schema schemas.
SkillCFreshness: CClaude Code +9 - 0.469score
evidence-chain
ProfRandom92
Design evidence schemas, validate serialization, and plan hash chains.
SkillCFreshness: CClaude Code +9 - 0.466score
comptext-local-autonomy
ProfRandom92
Offline local-only autonomous workflow in CompText.
SkillCFreshness: CClaude Code +9 - 0.465score
comptext-pr-review-memory
ProfRandom92
Preserve compact PR review memory for dry-run CompText token-saving workflows.
SkillCFreshness: CClaude Code +9 - 0.465score
repo-hygiene
ProfRandom92
Clean stale local paths, align metadata, and verify gitignore.
SkillCFreshness: CClaude Code +9 - 0.464score
workspace-state
ProfRandom92
Prepare future local WorkspaceSnapshot and WorkspaceDelta support.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 7, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/ProfRandom92/Comptext
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ProfRandom92
- 0.469score
ci-validation
ProfRandom92
Manage GitHub Actions validation workflows and Python compatibility.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-status
ProfRandom92
View a summary of active workspace file presence and local diagnostics status.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-subagent-inventory
ProfRandom92
Inspect local subagent definitions, allowed file scopes, and routing matrix.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-workspace-validation
ProfRandom92
Validate workspace snapshot and delta files against JSON Schema schemas.
SkillCFreshness: CClaude Code +9 - 0.469score
evidence-chain
ProfRandom92
Design evidence schemas, validate serialization, and plan hash chains.
SkillCFreshness: CClaude Code +9 - 0.469score
comptext-local-boundaries
ProfRandom92
Audit project doctor files and verify the containment boundaries.
SkillCFreshness: CClaude 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 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.
Cite this page
pr-review-memory skill. Agent Mart. https://agentmart.dev/skills/profrandom92-pr-review-memory (last updated 2026-10-24)