Agents for Codex

av/harbor

Agent Codex

Evaluate expectations against an execution transcript and outputs.

marin-community/marin

Agent Codex

An expert, pragmatic ops/SRE persona on a long-running mission to incrementally rebuild Marin's ops stack into something self-documenting and reproducible. Use it to survey an operational area (cluster rollout, GCS buckets, Iris↔Finelog wiring, GitHub integrations, auth, autoscaling), find the highest-leverage…

heyitsnoah/claudesidian

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

heyitsnoah/claudesidian

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

heyitsnoah/claudesidian

Agent Codex

Evaluate expectations against an execution transcript and outputs.

NVIDIA-NeMo/DataDesigner

Agent Codex

Search local Fern documentation for content related to a topic. Use this agent when the user wants to find documentation about a specific feature, concept, or usage pattern. Proactively use this when answering questions that might be covered in the project documentation.

NVIDIA-NeMo/DataDesigner

Agent Codex

Search GitHub issues, discussions, and PRs for content related to a topic. Use this agent when the user wants to find existing GitHub issues, pull requests, or discussions about a specific topic, feature, bug, or code pattern. Proactively use this when researching whether something has been discussed or implemented…

carlvellotti/free-ai-courses

Agent Codex

Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.

carlvellotti/free-ai-courses

Agent Codex

Strategic framing, executive communication, and stakeholder alignment specialist. Use when converting technical updates to executive summaries, framing work for leadership, writing business cases, or getting advice on stakeholder communication.

carlvellotti/free-ai-courses

Agent Codex

User research analysis, pain point identification, and qualitative insight synthesis. Use when analyzing user interviews, synthesizing research findings, identifying user pain points, refining personas, or extracting insights from support tickets and feedback.

silvertakana/worldwideview

Agent Codex

Use proactively before merging changes that touch authentication, authorization, plugin execution, API routes, JWT handling, or the marketplace install bridge. Read-only security audit focused on the WWV attack surface. Triggers on "security review", "check for vulnerabilities", "audit the auth flow", "review before…

first-fluke/oh-my-agent

Agent Codex

Documentation drift detection and sync specialist. Use to update docs//.md after code changes, verify broken refs, and apply patches reflecting recent diffs.

first-fluke/oh-my-agent

Agent Codex

Behavior-preserving refactoring specialist. Hotspot repayment, characterization-test safety nets, atomic refactor-only commits. Never changes observable behavior.

first-fluke/oh-my-agent

Agent Codex

Cross-source research specialist. Freely traverses web/docs/code search, community/market signals, and academic literature to answer open questions with cited, trust-labeled, triangulated findings.

huytieu/COG-second-brain

Agent Codex

Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack.

huytieu/COG-second-brain

Agent Codex

Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per orchestrator cycle.

huytieu/COG-second-brain

Agent Codex

Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge without human promotion.

toonight/get-shit-done-for-antigravity

Agent Codex

Diagnoses one issue with hypothesis-driven debugging on a clean context, applying the 3-strike rule. Invoke from /debug when a polluted context has stopped making progress.

toonight/get-shit-done-for-antigravity

Agent Codex

Executes exactly one GSD PLAN.md with atomic per-task commits, deviation handling, and a SUMMARY.md artifact. Invoke once per plan so every plan execution starts from a clean context.

toonight/get-shit-done-for-antigravity

Agent Codex

Runs discovery — codebase mapping or technical research for a phase — and writes the findings to disk. Invoke from /map, /plan, and /research-phase so exploration never lands in the orchestrator's context.

pydantic/pydantic-ai-harness

Agent Codex

Use as the final documentation gate before a capability PR merges. Verifies that a user-facing change keeps the capability README and its unified-docs page in sync with each other and with the code, that every snippet is runnable, and that links follow repo convention. Reports gaps; does not edit.

kdlbs/kandev

Agent Codex

Read-only, low-cost PR monitor. Use only after the user explicitly asks to wait for CI or review updates.

LedgerHQ/ledger-live

Agent Codex

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences.

LedgerHQ/ledger-live

Agent Codex

Code review expert for Ledger Wallet apps (ledger-live-desktop & ledger-live-mobile). Use proactively after code changes to check MVVM compliance, Lumen UI usage, new dependencies, Sonar issues, and security.