Skip to content
~/agentops
GitHubInstall
// 12-FACTOR AGENTOPS

Don't run production
on vibes.

34 optional skills for Claude Code and Codex: investigate code, write useful tests, and independently review changes. Start with one task in a project you already work on. Your coding agent runs the work; your repository keeps its tests, tracker, and Git workflow.

Install and try Research →GitHub ↗Read the 12 factors →

// start with the work in front of you

Skills are independent choices. Research, Test, and Refactor use your coding agent and repository tools; ao is optional for these tasks.

taskskillwhat you get
Understand a behaviorResearchA trace through code and tests, with file references and gaps.
Cover a missing edge caseTestA regression test plus the commands and results.
Simplify working codeRefactorA focused change checked against existing behavior.
Try the read-only Research task →

// the 12 factors

all 12 →

Four tiers a unit of work passes through: Brief the Agent, Lay the Rails, Gate the Work, Govern the Loop. Govern feeds back into the next brief.

BRIEF THE AGENTI - IIIcompile what the actor needs
IPacketsPass exact intent and bounded evidence between roles; leave the author transcript behind.IIGround TruthKeep work state, decisions, and learnings in git so the next session reads the repo, not a dead chat.IIIScopeGive each job the smallest sufficient agent; a one-shot task gets no orchestration.
LAY THE RAILSIV - VIconstrain where work can go
IVBlast RadiusBound what an agent can touch and spend: capabilities, budget, steps, attempts.VPaveResearch the terrain first, then pave it with instructions, contracts, and tests.VILanesGive each concurrent worker exclusive ownership of what it edits; claims are not locks.
GATE THE WORKVII - IXdecide what survives
VIIVerdictThe author supplies evidence; a fresh context judges the exact intent, scope, and result.VIIIRatchetLand accepted work with its proof so later changes can test against that floor.IXLearnUse Beads for the work trail and a reviewed LLM wiki for reusable, source-linked knowledge.
GOVERN THE LOOPX - XIIsteer the system
XOwnBuild and own the verdict machinery; rent the orchestration around it.XIStopReport ambiguity or failure and stop; the caller decides whether another run exists.XIIPriceTrack what verified work costs and drive it toward the cost of unverified work.

// the three gaps they address

Three failure modes. Each one has a named operating surface.

G1JUDGMENTA fresh reviewer checks the exact change against the accepted request.addressed by native checks · fresh independent review
G2DURABLE CONTEXTYour tracker preserves work; optional reviewed memory preserves reusable knowledge.addressed by your tracker · optional reviewed memory
G3LOOP CLOSUREFinish against the accepted request; persist a verdict when requested.addressed by accepted intent · checks · fresh judgment

// the boundary

INDEPENDENT REVIEW · Accepted intent → native implementation and checks → fresh independent judgment → finish. AgentOps helps a fresh reviewer check the exact change against your request. Persist a verdict when requested; your repository owns Git, merge, release, and rollback.

Your tracker preserves work. Optional reviewed memory preserves reusable knowledge and its sources.
Review decides what enters memory. A later task links what it needs. The model does not learn merely because a session ended. See the maintenance loop →
// your agent said done; something else proved it. the proof is yours.
make the change inspectable