Skills, all optional.

Each skill is a plain-Markdown SKILL.md you can read before you use it. Your agent loads one when its description fits the task. A clear task can finish with none of them.

Name a skill to invoke it

Claude Code/agentops:research

Codex$agentops:research

Or just say“Use AgentOps Test to cover this edge case.”

Pinned to AgentOps v3.11.0, released 2026-10-22. Names and summaries come from each SKILL.md at that tag. Changes are in the release notes; dependencies and effects per skill are in the skill router.

Primary entrypoints

Independent choices, not a required sequence.

planSKILL.md ↗Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions.Use when: planning, breaking down or scoping a change.implementSKILL.md ↗Change or repair code, config or services without weakening tests; report what ran and what did not.Use when: implementing a change or fixing a defect.reviewSKILL.md ↗Give advisory feedback on a plan, design or code change.Use when: asked for an opinion or a look-over, even informally. Not for acceptance; use Validate.validateSKILL.md ↗Freshly judge whether a finished change and its claims meet original acceptance: PASS, FAIL or NOT_PROVEN.Use when: asked for a go/no-go, sign-off or independent verdict.orchestrateSKILL.md ↗Coordinate several workers: what idle agents do next, which finished work gets checked first, how to recover a dead one.Use when: managing multiple agents.memorySKILL.md ↗Find or curate supported lessons and agent rules.Use when: asked to remember, trace a corrected claim, audit instructions or write an agent rule.

Engineering specialists

architectureCompare interface designs and find structural friction.Use when: a change spreads across modules or a boundary is unclear. For code changes, use Refactor.docWrite source-checked docs, READMEs, change descriptions and handoffs.Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.domainSettle what domain terms mean per context, and which repository conventions or language standards (Go, Python) apply.Use when: names disagree or a rename is proposed.ergonomicsAudit CLI, API, MCP or SDK discovery, first use and error recovery.Use when: designing an agent-facing tool or investigating misuse, including one command.refactorRestructure or clean up code with no behavior change, proved by before-and-after checks.Use when: asked to clean up, extract, dedupe or simplify, even one function.researchAnswer one cited question about code, history, claims or patterns.Use when: asked how it works, why it changed, whether a claim holds or a pattern warrants a rule.reverse-engineerTear down a competitor's repo or product into a feature inventory and adoption choices.Use when: comparing us to another tool or asking what to steal.securityReview code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks.Use when: asked whether code is safe to ship, even one small handler.skill-builderCreate, repair, audit or consolidate agent skills (SKILL.md packages).Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.skill-evalMeasure whether a skill helps by comparing runs with and without it.Use when: reading skill A/B results or deciding to keep, revise or remove one.testWrite or assess tests that prove behavior and would fail without the fix.Use when: writing tests, TDD, or asked whether a green test is enough.triageTurn incoming reports, external PRs and alerts into evidence-based decisions and agent-ready briefs.Use when: intake arrives. For accepted work, use Plan.

Deliberate planning and review strategies

councilCompare independent opinions from several models or contexts without inflating agreement.Use when: wanting a second opinion or debate, or summarizing several reviewers' results.craft-goalDraft or lint a bounded long-running goal prompt with a finish line and hard limits.Use when: selected by name; one change goes to Plan.idea-genieBrainstorm evidence-backed options for what to build, or stress-test an idea.Use when: deciding what to build next, comparing options or testing an idea.interviewInterview you one question at a time, each choice with a recommendation, to settle a big outcome before agents work alone.Use when: selected by name.navigatePick the next work in an epic or bead graph; closed is not proven.Use when: asked what is next or whether an epic is done.postmortemExplain why a change, incident or session went as it did, separating proven causes from coincidence.Use when: a postmortem or retro is selected by name.premortemFind how a rollout plan could fail before committing to it.Use when: asked what could go wrong or to poke holes in a plan.reality-checkAudit claims that work is done or shipped against the diff or repo.Use when: asked whether something really got done, even if it looks obvious.rpiDrive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly.Use when: selected by name.

Explicit tool and runtime adapters

agent-nativeDispatch independent tasks to parallel workers or subagents without write collisions.Use when: running or planning agents in parallel, even two; check scopes before any launch.agy-nativeRun a supplied task in headless AGY (Antigravity, Gemini) and collect its result.Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.claude-execRun one prompt through headless Claude with scoped permissions and a time bound.Use when: scripting or automating a `claude -p` call, even a simple one.codex-execRun one prompt through headless Codex and capture the result.Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.using-gcOperate Gas City through its own doors: Mayor, doctor and native run state.Use when: Gas City is selected or a gc run looks stuck.

Works alongside

Independently distributed; install them from their authors. External tool skills are no longer bundled with AgentOps.

Gas CityConfigurable runtime providers, work routing, workflow packs and supervision. AgentOps ships a using-gc adapter and an executor pack.

Agentic Coding FlywheelTools and workflows for a multi-agent development environment. Add AgentOps skills to the coding agents you use there.

Destructive Command GuardChecks shell commands and blocks covered destructive operations.

CASSIndexes and searches coding-agent session histories, as evidence for Memory or new work.

Meta SkillCan mine selected CASS sessions into reusable skill candidates with source links.

The Flywheel, DCG, CASS and Meta Skill are Jeffrey Emanuel’s projects.

Try one skill on your own repository.

The install page walks through one read-only Research task.

Install AgentOps