kairos

Plugin kairos from marketplace kairos-agents-framework in diego81b/kairos-agents-framework. Commands read from the repo's manifest — 24 days ago.

Skills (11)

• agent-contract

  Shared missing-input error format used by every phase agent's own Input Validation section, parameterized by the agent's own name.

• analysis-discipline

  Engineering-discipline checklist for analysis and review work — evidence-backed findings, restraint on low-value nitpicks, scope-bounded investigation, and brief direct pushback when evidence contradicts the requested approach. Applied throughout requirement, architecture, and review phases, distinc

• artifact-bookkeeping

  Deterministic bookkeeping rules for phase artifacts — tallying Risk/Issue/Finding tables by Impact and deriving each phase's pass/fail status from those counts. Shared reference for every agent that emits risk_counts/issues_summary/findings_summary and a status field.

• artifact-template

  Shared body skeleton for every KAIROS phase artifact — the mandatory Summary head block that makes a gate readable in seconds, and the fixed column sets for any table the orchestrator's Risk Disposition Loop parses. Invoked by every agent that writes a .kairos/ phase artifact.

• code-simplification

  Refactoring checklist for simplifying code without changing behavior. Resolves what to simplify, how to verify behavior is preserved, and when to stop — for the REFACTOR step of implementation.

• coding-discipline

  Engineering-discipline checklist for writing new code — scope control, anti-overengineering, assumption surfacing, and verifiable success criteria. Applied before and during implementation, distinct from the REFACTOR-time code-simplification checklist.

• constraint-taxonomy

  Closed vocabulary for the ledger's constraint Category column, plus the reader, writer, and gating rules that let a review section run only when its obligation was explicitly declared upstream. Invoked by every agent that creates or updates a constraints.md row, and by every conditional check gated

• contract-checklist

  Pre-implementation checklist for API and database contracts. Resolves entity lifecycle, payload shape, ownership/IDOR risk, idempotency, delete behavior, aggregate update semantics, pagination, versioning, and error shape before any contract is finalized.

• issue-tracker-comment

  Shared jira/glab/bitbucket comment-posting commands for the optional "post this phase's output to the issue tracker" step every phase agent offers, parameterized by output file and comment title.

• migration-safety

  Safety checklist for schema and data migrations. Resolves expand/contract sequencing, lock duration, backfill restartability, reversibility, and what a code rollback does to data already written in the new shape — before the migration is designed and again before the rollback plan is written.

• threat-model

  Design-time threat modelling checklist. Resolves trust boundaries, attack surface, who can reach what, what an attacker controls, and what crossing a boundary costs — before any contract is finalized and before any code exists to review.

Slash commands (3)

• /kairos:setup

  Guided KAIROS model setup — pick per-tier models and write them to .kairos-cfg/models (this project or your home folder)

• /kairos:usage

  Show which model each KAIROS agent really used and how many tokens it spent, measured from the session transcripts

• /kairos:view

  Render one KAIROS phase artifact as a synthetic, human-readable HTML page

Subagents (17)

• architect-agent

  Designs system architecture based on requirements and constraints. Use after PM analysis.

• bug-triage-agent

  Standalone agent for incoming bug reports. Reproduces the defect, isolates it, finds the root cause with evidence, rates severity, and recommends where the fix re-enters the pipeline. Never fixes anything itself. Use when what you have is a bug report rather than a feature request. Produces 00c-bug-

• code-reviewer-agent

  Reviews code for quality, standards, security, and performance.

• context-extractor-agent

  Scans a codebase and an issue draft to produce 00-context.md for downstream agents. Use before orchestrator to prepare LLM context.

• dependency-audit-agent

  Standalone, periodic agent. Audits the whole project's dependencies and accumulated technical debt — known CVEs, stale versions, license conflicts, unused and duplicated packages, debt hotspots — and produces a prioritized backlog a human can feed into the pipeline. Never applies an upgrade itself.

• documentation-agent

  Optional Phase 6b agent. Writes feature-facing documentation (README, API reference, CHANGELOG) in the target project after release planning. The second agent, after the Phase 3 implementer, permitted to write outside .kairos/ — scoped strictly to documentation files, never source code. Use when API

• impact-assessment-agent

  Issue-scoped grounding agent. Reads the issue and the code it touches to estimate effort, map domains, surface reusable assets and gaps, and report the facts the orchestrator derives the pipeline from. Started by the orchestrator at its Step 0e, or by you before it. Produces 00b-impact.md.

• implementer-coder-agent

  Code-first implementer — writes the code, then adds or updates the tests the project and the touched modules call for, as decided in its plan's Test Decision. Chosen by the orchestrator for simple_fix, for projects without a test suite, and when the design says test_first: no. implementer-tdd-agent

• implementer-tdd-agent

  TDD implementer — generates code and tests using real TDD (RED→GREEN→REFACTOR). Chosen by the orchestrator when the project has a test suite and the design can be stated as tests first (architect's test_first: yes). implementer-coder-agent is the code-first counterpart.

• improvement-advisor-agent

  Standalone, infrequent agent. Reads the accumulated cross-feature .kairos/_lessons.md, looks for patterns confirmed across 3+ past features, and proposes concrete KAIROS framework edits as ADR-style records for a human to apply manually — never self-edits agents/*.md. Use every few features, not eve

• orchestrator-agent

  Master coordinator for KAIROS Framework. Routes feature requests to specialist subagents and orchestrates the workflow.

• pm-agent

  Analyzes feature requirements and elicits constraints. Use when you have a vague feature request that needs structured analysis.

• qa-plan-agent

  Optional Phase 5b agent. Plans the verification automated tests cannot give — manual and exploratory test cases, regression retest selection, test data and environment needs, and UAT sign-off criteria. Grounded in test-verifier's real coverage gaps and the shipped diff, never in the feature request

• release-planner-agent

  Plans deployment strategy and rollback procedures.

• retrospective-agent

  Standalone post-pipeline agent. Reads a finished feature's own KAIROS artifacts and ledger to synthesize distilled lessons, appended to the project-wide .kairos/_lessons.md log. Use any time after work on a feature stops (not necessarily after Phase 6 — a simple_fix that never ran release-planner-ag

• security-reviewer-agent

  Adversarial security review of implementation code. Finds exploitable vulnerabilities ranked by real severity with attack scenarios. Runs in the review wave alongside code-reviewer-agent and test-verifier-agent, or after code-reviewer-agent when invoked standalone.

• test-verifier-agent

  Verifies test quality, coverage adequacy, assertion strength, determinism, and TDD compliance. Loops back to implementer with actionable findings.

Similar plugins