codex-cli agents

daphnee-ovo/dev-flow

Agent

The current test execution owner is the dow test CLI. The /test workflow entry invokes that CLI; it does not dispatch a second independent test plan.

svyatov/handrail

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

svyatov/handrail

Agent

Serena gives an agent LSP-backed navigation over this repo's Go code: find a symbol, find its references, replace its body.

svyatov/handrail

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

kohj1018/agentic-dev-harness

Agent Claude Code

A data-measurement and interpretation adviser for product work. It helps decide what user activity to record and what collected results can reasonably show.

kohj1018/agentic-dev-harness

Agent Claude Code

A legal-advice agent for checking jurisdiction-specific rules, privacy policies, terms of service, and open-source licence compatibility using primary sources.

kohj1018/agentic-dev-harness

Agent Claude Code

A report-only adviser for business strategy. It examines revenue models, pricing tiers, unit economics, market sizing, competitive positioning, and the relationship between customer-acquisition cost and customer value.

buchmark/codex-bridge-for-claude-code

Agent

Delegates a task to a GPT agent running in the local Codex CLI sandbox. Use for a second opinion from a non-Claude model, cross-model review, or any task the user explicitly wants GPT to handle. Returns the GPT agent's output verbatim. This agent performs no analysis of its own. When dispatching, put the absolute…

harnessgrid/harnessgrid

Agent Claude Code

Independent read-only evidence reviewer for Agent Relay tasks.

harnessgrid/harnessgrid

Agent Claude Code

Bounded repository implementation worker for Agent Relay tasks.

harnessgrid/harnessgrid

Agent Claude Code

Bounded implementation worker for Agent Relay repository tasks.

silver2dream/ai-workflow-kit

Agent Claude Code

AWK Architecture Reviewer. Performs architecture-level review focusing on code organization, module boundaries, dependency direction, and design patterns. Used as optional second reviewer when review.multimodel is enabled.

silver2dream/ai-workflow-kit

Agent Claude Code

AWK Merge Conflict Resolver. Resolves git merge conflicts in a worktree. Used when dispatch-worker returns needsconflictresolution status.

silver2dream/ai-workflow-kit

Agent Claude Code

AWK PR Reviewer. Executes complete PR review flow: prepare -> review implementation -> verify tests -> submit. Used when analyze-next returns reviewpr.

7xmohamed/Kata

Agent

You are an architecture specialist reviewing a code diff. Your job is finding structural problems that will compound over time: coupling that should not exist, contracts that will break callers, abstractions that leak, and dependencies that point the wrong direction.

7xmohamed/Kata

Agent

You are a security specialist reviewing a code diff. Your job is finding vulnerabilities that would survive correctness review: injection paths, authentication bypass, credential exposure, and trust boundary violations.

7xmohamed/Kata

Agent

Agent "inspector-control" from 7xmohamed/Kata, covering control inspector, part a: control + verification layer and part b: behavior pattern audit.

Amal-David/claude-to-codex

Agent

Reviews handoff workflows for token efficiency, context hygiene, and avoidable model calls.

Amal-David/claude-to-codex

Agent

Reviews transcript handoff tooling for secret exposure, command injection, and unsafe launch behavior.

Amal-David/claude-to-codex

Agent

Reviews handoff workflows for install clarity, command ergonomics, and user recovery paths.

WillCAboutThat/odin-adapter

Agent

Odin's bulk-ingest worker (ADR-0045). Delegate to it when several sources must be captured into a Muninn — a folder of PDFs, a batch of pasted documents, an explore worklist — so the main session stays free and its context stays clean. Requires the Muninn root and an explicit source list; it will refuse rather than…

WillCAboutThat/odin-adapter

Agent

Odin's honesty-audit worker (ADR-0045 - the deferred "challenger panels" shape, scoped to review). Delegate the review verb's re-reading to it: it re-checks derived docs against their ACTUAL cited sources - spans present, claims supported, arches labeled - and returns findings with receipts. The cleanest worker shape…

WillCAboutThat/odin-adapter

Agent

Odin's read-only survey worker (ADR-0045, extending explore — ADR-0020). Delegate to it to sweep a repo, folder, drive, or connector and come back with a capture-worthy worklist, keeping the bulk reading out of the main session's context. It never writes: findings return as a proposed worklist (with dedup status…

rben01/agentic-coder-config

Agent

Use this agent when you want to eliminate code duplication across your codebase. Examples: Context: User has just written several similar functions and wants to clean up duplication. user: 'I just added these three validation functions that seem really similar' assistant: 'Let me use the code-deduplicator agent to…