Context Map
Generated by npm run context-map. Regenerate after changing agents, skills, schemas, workflow contracts, or core commands.
How To Use This
- Start here when a session is long, resumed, or context-constrained.
- Load only the specific skill, contract, schema, or doc that matches the task.
- Treat
.kontourai/flow-agentsas runtime state anddist/as generated output.
Repository Shape
| Path | Role | Purpose |
|---|---|---|
| agent-cards | canonical copy | Install/discovery cards that point at canonical agents. |
| agents | source | Canonical agent specs and routing prompts. |
| context | canonical copy | Shared contracts, routing notes, templates, and reusable guidance. |
| docs | canonical copy | Long-lived project documentation and GitHub Pages content. |
| evals | canonical copy | Static, integration, install, and behavioral eval fixtures. |
| kits | canonical copy | Project directory. |
| packaging | canonical copy | Project directory. |
| powers | canonical copy | Optional MCP/tool capability bundles. |
| prompts | canonical copy | Reusable prompt entry points. |
| schemas | canonical copy | JSON Schema contracts for machine-readable workflow artifacts. |
| scripts | canonical copy | Build, validation, hook, telemetry, workflow, and import/export utilities. |
| skills | canonical copy | On-demand capability instructions and workflow primitives. |
| dist | generated | Generated bundle exports. Do not edit by hand. |
| .kontourai/flow-agents | runtime | Non-durable workflow artifacts, sidecars, and generated projections. Not committed by default. |
| .flow-agents | durable local state | Explicit Flow Agents config/install state. Not a runtime artifact fallback. |
Core Commands
| Use | Command | ||
|---|---|---|---|
| Source tree | npm run validate:source | ||
| Static suite | bash evals/run.sh static | ||
| Integration suite | bash evals/run.sh integration | ||
| Workflow artifacts | npm run workflow:validate-artifacts – –require-sidecars –require-critique .kontourai/flow-agents/ |
||
| Workflow control | flow-agents workflow –help | ||
| Workflow status | flow-agents workflow status –session-dir .kontourai/flow-agents/ |
||
| Workflow critique | flow-agents workflow critique –session-dir .kontourai/flow-agents/ |
fail | not_verified> –summary |
| Workflow verification | flow-agents workflow evidence –session-dir .kontourai/flow-agents/ |
fail | not_verified> –command “bash evals/static/test_builder_skill_coherence.sh” –criterion-json ‘{“id”:”AC-1”,”status”:”pass”,”evidence_refs”:[{“kind”:”command”,”excerpt”:”bash evals/static/test_builder_skill_coherence.sh”,”summary”:”Exact substantive command run for AC-1.”}]}’ –evidence-ref-json ‘{“kind”:”artifact”,”file”:”.kontourai/flow-agents/ |
| Context map drift | npm run context-map:check | ||
| Bundle build | npm run build:bundles | ||
| Skill drift check | flow-agents skill-drift-check |
Workflow Sidecars
Machine-readable workflow state lives beside Markdown artifacts in .kontourai/flow-agents/<slug>/.
| Schema | Title | ID |
|---|---|---|
| assignment-provider-settings.schema.json | Flow Agents Assignment Provider Settings | https://flow-agents.dev/schemas/assignment-provider-settings.schema.json |
| backlog-provider-settings.schema.json | Flow Agents Backlog Provider Settings | https://flow-agents.dev/schemas/backlog-provider-settings.schema.json |
| builder-lifecycle-authorization.schema.json | Builder Lifecycle Authorization | https://kontourai.dev/schemas/builder-lifecycle-authorization.schema.json |
| change-provider-settings.schema.json | Flow Agents Change Provider Settings | https://flow-agents.dev/schemas/change-provider-settings.schema.json |
| decision-record.schema.json | Flow Agents Decision Record | https://flow-agents.dev/schemas/decision-record.schema.json |
| flow-agents-settings.schema.json | Flow Agents Settings | https://flow-agents.dev/schemas/flow-agents-settings.schema.json |
| grounded-execution-narrative.schema.json | Flow Agents Grounded Execution Narrative | https://flow-agents.dev/schemas/grounded-execution-narrative.schema.json |
| lifecycle-authority-keys.schema.json | Lifecycle Authority Key Registry | https://kontourai.dev/schemas/lifecycle-authority-keys.schema.json |
| narrative-eval-result.schema.json | Flow Agents Narrative Eval Result | https://flow-agents.dev/schemas/narrative-eval-result.schema.json |
| narrative-runtime-projection.schema.json | Flow Agents Grounded Runtime Projection | https://flow-agents.dev/schemas/narrative-runtime-projection.schema.json |
| narrative-source-manifest.schema.json | Flow Agents Narrative Source Manifest | https://flow-agents.dev/schemas/narrative-source-manifest.schema.json |
| retrospective-observation-manifest.schema.json | Flow Agents retrospective observation input manifest | https://kontourai.dev/schemas/flow-agents/retrospective-observation-manifest/1.0.json |
| retrospective-observation.schema.json | Flow Agents privacy-safe retrospective run observation | https://kontourai.dev/schemas/flow-agents/retrospective-observation/1.0.json |
| run-correlation-envelope.schema.json | Run correlation envelope | https://kontourai.dev/schemas/flow-agents/run-correlation-envelope/1.0.json |
| workflow-acceptance.schema.json | Flow Agents Workflow Acceptance | https://flow-agents.dev/schemas/workflow-acceptance.schema.json |
| workflow-critique.schema.json | Flow Agents Workflow Critique | https://flow-agents.dev/schemas/workflow-critique.schema.json |
| workflow-evidence.schema.json | Flow Agents Workflow Evidence | https://flow-agents.dev/schemas/workflow-evidence.schema.json |
| workflow-handoff.schema.json | Flow Agents Workflow Handoff | https://flow-agents.dev/schemas/workflow-handoff.schema.json |
| workflow-learning.schema.json | Flow Agents Workflow Learning | https://flow-agents.dev/schemas/workflow-learning.schema.json |
| workflow-outcome.schema.json | Flow Agents workflow outcome record | https://kontourai.dev/schemas/flow-agents/workflow-outcome/1.0.json |
| workflow-release.schema.json | Flow Agents Workflow Release Readiness | https://flow-agents.dev/schemas/workflow-release.schema.json |
| workflow-state.schema.json | Flow Agents Workflow State | https://flow-agents.dev/schemas/workflow-state.schema.json |
| workflow-waves.schema.json | Flow Agents Workflow Waves | https://flow-agents.dev/schemas/workflow-waves.schema.json |
Primary tools: public flow-agents workflow, trust.bundle, artifact validation, scripts/hooks/stop-goal-fit.js, and scripts/hooks/workflow-steering.js. The package-internal writer is not an agent or consumer interface.
Workflow Skills
| Skill | Source | When To Load |
|---|---|---|
| continue-work | kits/builder/skills/continue-work/SKILL.md | Explicit Builder Kit continuation extension. Prepares a fresh-context handoff for the next unfinished increment of a multi-slice Work Item. |
| deliver | kits/builder/skills/deliver/SKILL.md | Builder Kit build entrypoint. Starts or continues a selected Work Item through builder.build by composing the build primitives without owning their step evidence. |
| evidence-gate | kits/builder/skills/evidence-gate/SKILL.md | Assess whether verification evidence and scope integrity support merge review. Produces a confidence report and Builder merge-readiness evidence. |
| execute-plan | kits/builder/skills/execute-plan/SKILL.md | Execution primitive that turns a structured plan into implemented scope through tool-worker delegation. |
| fix-bug | kits/builder/skills/fix-bug/SKILL.md | Bug-fix profile for builder.build. Adds disciplined diagnosis and regression-focused verification without replacing the build primitives. |
| gate-review | kits/builder/skills/gate-review/SKILL.md | Explicit advisory extension for reviewing apparent workflow gate blocks or misses from a completed trust bundle. |
| idea-to-backlog | kits/builder/skills/idea-to-backlog/SKILL.md | Turn raw product or technical ideas into a shaped, prioritized, provider-neutral executable backlog before implementation starts. |
| learning-review | kits/builder/skills/learning-review/SKILL.md | Capture delivery decisions, outcomes, and routed follow-up. Records Builder publish-learn learning evidence in trust.bundle. |
| plan-work | kits/builder/skills/plan-work/SKILL.md | Code planning primitive that turns a goal and directory into a structured implementation plan. |
| pull-work | kits/builder/skills/pull-work/SKILL.md | Select ready provider-backed work and prepare a bounded implementation handoff. |
| release-readiness | kits/builder/skills/release-readiness/SKILL.md | Make a provider-neutral merge, release, deploy, or hold decision. Records Builder publish-learn CI merge-readiness in trust.bundle. |
| review-work | kits/builder/skills/review-work/SKILL.md | Report-only critique before Builder verification. Records a critique slice through the public workflow interface without claiming Flow completion. |
| tdd-workflow | kits/builder/skills/tdd-workflow/SKILL.md | Test-first profile for builder.build. Requires observable RED, GREEN, and appropriate REFACTOR evidence through the standard build primitives. |
| verify-work | kits/builder/skills/verify-work/SKILL.md | Report-only acceptance verification. Records command-backed Builder verification evidence in trust.bundle when bound to an active run. |
Support Skills
| Skill | Source | When To Load |
|---|---|---|
| agentic-engineering | skills/agentic-engineering/SKILL.md | Eval-first execution, task decomposition, and cost-aware model routing for AI-driven development workflows. |
| browser-test | skills/browser-test/SKILL.md | Headless browser automation via Playwright — screenshots, accessibility checks, form filling, UI testing, DOM inspection. |
| builder-shape | kits/builder/skills/builder-shape/SKILL.md | Builder Kit shaping entrypoint. Turns a raw idea into a provider-neutral, reviewable backlog proposal and stops before build selection unless the user explicitly continues. |
| dependency-update | skills/dependency-update/SKILL.md | Analyze and upgrade project dependencies — latest versions, security vulnerabilities, actionable update plan across all package managers. |
| design-probe | kits/builder/skills/design-probe/SKILL.md | Generic one-question-at-a-time design probe for turning unclear goals, designs, and handoffs into shared understanding. |
| eval-rebuild | skills/eval-rebuild/SKILL.md | Project-specific build and install commands for the eval feedback loop. Injected into eval-builder agent. Replace this skill for different build systems. |
| github-cli | skills/github-cli/SKILL.md | Interact with GitHub via gh CLI — PRs, issues, repos, releases, workflows, gists. |
| knowledge-capture | kits/knowledge/skills/knowledge-capture/SKILL.md | Save durable knowledge, lightweight pointers, user corrections, decisions, lessons, relationship context, or source references into the knowledge base. Use when the user says save, remember, capture, file this, bookmark context, or when… |
| pickup-probe | kits/builder/skills/pickup-probe/SKILL.md | Provider-grounded pickup probe used at the Builder design-probe step before planning. |
| search-first | skills/search-first/SKILL.md | Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. |
Agents
| Agent | Model | Tools | Role |
|---|---|---|---|
| dev | claude-opus-4.6-1m | 1 | Development agent for coding tasks. Writes, modifies, and validates code following existing patterns. Delegates to specialists for domain-specific research when available. |
| tool-code-reviewer | claude-sonnet-4.6-1m | 8 | Delegate to me for code quality review. Analyzes readability, maintainability, patterns, DRY compliance, and produces structured review with severity levels. Separate from verification (build/test/lint). |
| tool-dependencies-updater | agi-nova-beta-1m | 8 | Delegate to me for updating your project dependencies - checks latest versions, identifies outdated packages, and finds security advisories across npm, PyPI, Cargo, Maven/Gradle, Go, NuGet, Ruby, PHP, Swift, Dart, Docker, Helm, Terraform… |
| tool-explore-config | kimi-k2.5 | 6 | Delegate to me for project configuration inspection - finds and summarizes configuration files and environment variables within a project |
| tool-explore-deps | kimi-k2.5 | 6 | Delegate to me for Dependency analysis - parses package manifests to identify tech stack and dependencies |
| tool-explore-entry | kimi-k2.5 | 6 | Delegate to me to find the Entry point of a project - locates main files, CLI commands, API routes, and exports |
| tool-explore-patterns | kimi-k2.5 | 6 | Delegate to me for Pattern detection - identifies architectural patterns, frameworks, and coding conventions |
| tool-explore-structure | kimi-k2.5 | 6 | Delegate to me to scout out the project structure - maps directory layout and identifies key folders in a codebase |
| tool-explore-tests | kimi-k2.5 | 6 | Delegate to me to find and understand testing strategies - locates test files and understands testing strategy |
| tool-planner | claude-sonnet-4.6-1m | 7 | Delegate to me for codebase analysis and execution planning. Explores code, identifies patterns and dependencies, and writes plan/sidecar artifacts under .kontourai/flow-agents. No production file modifications. |
| tool-playwright | claude-sonnet-4.6-1m | 25 | Delegate to me for browser automation, testing, and debugging - loading real pages, testing navigation, checking accessibility via structured snapshots, evaluating scripts, and visual verification. Anything that would otherwise require a… |
| tool-security-reviewer | claude-sonnet-4.6-1m | 7 | Delegate to me for security analysis. Checks OWASP Top 10, secrets detection, input validation, injection vulnerabilities, auth/authz, and rate limiting. Read-only analysis with shell for scanning tools. |
| tool-verifier | claude-sonnet-4.6-1m | 8 | Delegate to me for implementation verification. Read-only + shell for source code; writes review/evidence artifacts under .kontourai/flow-agents. Verifies acceptance criteria and produces PASS/FAIL/NOT_VERIFIED verdicts with evidence. No… |
| tool-worker | claude-sonnet-4.6-1m | 1 | Delegate to me for writing and developing source code for a project. Works best when a detailed plan can be provided. NO access to web tools. Can be used in parallel for any coding tasks that require trusted access to the write and shell… |
Optional Powers
| Power | Source |
|---|---|
| dependency-checker | powers/dependency-checker/POWER.md |
| playwright | powers/playwright/POWER.md |
Current Workflow State
Runtime workflow state is excluded from the committed map.
Regenerate locally with npm run context-map -- --include-runtime to include recent .kontourai/flow-agents state.
Context Loading Rules
- For delivery work, load
deliver, then the specific primitive skill for the current phase. - For planning, verification, release, learning, or artifact validation, load
context/contracts/artifact-contract.mdplus the phase contract. - For unknown external APIs or libraries, use
search-firstbefore implementation. - For large or noisy sessions, prefer sidecars and this map over rereading broad docs.
- For generated exports, edit source files and rebuild instead of editing
dist/.