opencode-reviewer
List and inspect installed OpenCode reviewer roles, select an appropriate exact role, and launch or collect an isolated code or security review with verified…
Skill by upiscium
Chalk Labs
Need help deploying opencode-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/upiscium-opencode-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: security, 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
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/opencode-reviewer
What's inside
- Skill name
opencode-reviewer- Description
- List and inspect installed OpenCode reviewer roles, select an appropriate exact role, and launch or collect an isolated code or security review with verified agent binding and OpenCode-configured model selection. Use for independent reviews through OpenCode, reviewer startup failures, or explicit Reviewer-role requests. Provides interim routing until the repository's KUMIKI/KAGARI lifecycle owns it.
- License
- unknown
- Instructions
- 82 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- SKILL.md
- openai.yaml · agents/
- icon.svg · assets/
- launch.md · references/
- list_reviewers.mjs · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from upiscium/ChatGPT-Skills
- 0.565score
security-plan
upiscium
Convert selected findings from a security audit into a private-ready, Codex-executable remediation and patch implementation plan without modifying code or…
SkillAFreshness: AClaude Code +9 - 0.565score
security-audit
upiscium
Perform an evidence-backed defensive security audit of a specific GitHub branch, commit, or branch diff using threat modeling and technology-appropriate checks.
SkillAFreshness: AClaude Code +9 - 0.565score
workspace-cleanup
upiscium
Inventory and safely clean up workflow-owned OpenCode runtimes, RDC-launched processes, tmux panes and sessions, temporary files and Git worktrees after…
SkillAFreshness: AClaude Code +9 - 0.565score
dev-loop
upiscium
Coordinate Arca planning, authorized OpenCode delegation, independent change review and human-executed merge through one verified checkpoint at a time.
SkillAFreshness: AClaude Code +9 - 0.565score
human-review
upiscium
Explain concrete approvals, identify unresolved human decisions, and independently audit missed decisions in bounded repository history.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-miner
upiscium
Analyze the current conversation, supplied transcripts, or handover material to identify reusable workflows that should become personal skills, distinguish…
SkillAFreshness: AClaude Code +9 - 0.560score
blueprint
upiscium
Turn a vague idea, desired capability or workflow pain into a human-approved design brief, stable acceptance criteria and bounded Issue candidates through an…
SkillAFreshness: AClaude Code +9 - 0.560score
debug-investigate
upiscium
Investigate a concrete test, CI, build, runtime or performance failure through bounded reproduction, boundary tracing and discriminating hypotheses.
SkillAFreshness: AClaude Code +9 - 0.560score
opencode-bridge
upiscium
Send a bounded authorized packet to an existing OpenCode session, inspect its state, collect evidence or deliver a resolved reply via a configured remote…
SkillAFreshness: AClaude Code +9 - 0.559score
handover
upiscium
Create a self-contained handover for continuing the current conversation in a new chat or with another agent.
SkillAFreshness: AClaude Code +9 - 0.559score
issue-filer
upiscium
Create deduplicated Bug or Feature Request Issues from explicitly selected merged-repository findings or human-approved blueprint design units.
SkillAFreshness: AClaude Code +9 - 0.559score
change-review
upiscium
Independently review one frozen prepublication change or GitHub pull request against approved intent, acceptance criteria and evidence.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Oct 14, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/upiscium/ChatGPT-Skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from upiscium
- 0.565score
security-plan
upiscium
Convert selected findings from a security audit into a private-ready, Codex-executable remediation and patch implementation plan without modifying code or…
SkillAFreshness: AClaude Code +9 - 0.565score
skill-miner
upiscium
Analyze the current conversation, supplied transcripts, or handover material to identify reusable workflows that should become personal skills, distinguish…
SkillAFreshness: AClaude Code +9 - 0.565score
dev-loop
upiscium
Coordinate Arca planning, authorized OpenCode delegation, independent change review and human-executed merge through one verified checkpoint at a time.
SkillAFreshness: AClaude Code +9 - 0.565score
human-review
upiscium
Explain concrete approvals, identify unresolved human decisions, and independently audit missed decisions in bounded repository history.
SkillAFreshness: AClaude Code +9 - 0.565score
security-audit
upiscium
Perform an evidence-backed defensive security audit of a specific GitHub branch, commit, or branch diff using threat modeling and technology-appropriate checks.
SkillAFreshness: AClaude Code +9 - 0.565score
workspace-cleanup
upiscium
Inventory and safely clean up workflow-owned OpenCode runtimes, RDC-launched processes, tmux panes and sessions, temporary files and Git worktrees after…
SkillAFreshness: AClaude 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 opencode-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
opencode-reviewer skill. Agent Mart. https://agentmart.dev/skills/upiscium-opencode-reviewer (last updated 2026-10-24)