Skip to content

Source index

Agent QC v0.4.0 is derived from local project inspection plus public documentation. Local repositories are case studies, not normative dependencies.

Last reviewed: 2026-05-10.

Citation format

Use source ids in design notes or changelogs:

text
[SRC-AGENTUI-BEST-PRACTICES] -> surface pass must link visible projection to runtime facts.

Local standards repositories

Source idSourceEvidence usedAgent QC requirements informed
SRC-AGENTUI-BEST-PRACTICES/Users/coso/Documents/dev/ai/limecloud/agentui/docs/en/authoring/best-practices.mdruntime-owned facts, event classes, stable ids, fallback states, controlled writes, old-session design, latency metricsAgent QC requires surface evidence to link visible frames to runtime/protocol facts and avoid UI-owned verdicts.
SRC-AGENTUI-ACCEPTANCE/Users/coso/Documents/dev/ai/limecloud/agentui/docs/en/authoring/acceptance-scenarios.mdsend/status, tool, HITL, queue/steer, artifact, evidence, old-session, team/parallel/remote/background scenariosAgent QC acceptance scenarios cover runtime, TUI, WebUI, team, remote, and eval flows.
SRC-AGENTUI-FLOW/Users/coso/Documents/dev/ai/limecloud/agentui/docs/en/reference/flow-and-taxonomy.mdlifecycle, event envelope, fact owners, scopes, phases, surfaces, controls, team taxonomyAgent QC flow/taxonomy mirrors explicit dimensions and fact-owner separation.
SRC-AGENTUI-CONTRACTS/Users/coso/Documents/dev/ai/limecloud/agentui/docs/en/contracts/*.mdbackend coordination, runtime event projection, performance metricsAgent QC adds evidence, performance, and reliability contracts for UI/TUI/desktop/browser gates.
SRC-AGENTKNOWLEDGE-SPEC/Users/coso/Documents/dev/ai/limecloud/agentknowledge/docs/en/specification.mddirectory-as-standard, progressive disclosure, source maps, compile/eval evidence, knowledge-as-data boundaryAgent QC keeps Knowledge as requirements/context input, not proof, and preserves source traceability.

Local project case studies

Source idSourceUse
SRC-CODEX-LOCAL/Users/coso/Documents/dev/rust/codexRuntime CLI, Rust, Bazel, cargo nextest, SDK, MCP, app-server protocol, sandbox, process cleanup, TUI snapshots, schema fixtures, release patterns.
SRC-CLAUDECODE-LOCAL/Users/coso/Documents/dev/js/claudecodePartial local source snapshot for Ink TUI, remote bridge, WebSocket control, permission flow, SDK stream adapter, commands, task/team surfaces; not enough metadata for CI/release claims.
SRC-OPENCLAW-LOCAL/Users/coso/Documents/dev/js/openclawMulti-channel gateway, Vitest lane routing, UI browser-mode tests, QA Lab, live provider opt-in, Docker/install smoke, plugin/secret/channel contracts, mobile/platform scripts.
SRC-HERMES-LOCAL/Users/coso/Documents/dev/python/hermes-agentPython pytest, markers, xdist, integration/e2e separation, credential blanking, cron/scheduler, browser safety, gateway/channel tests, TUI Vitest, Docker/uv/OSV.

External public sources

Source idSourceEvidence usedAgent QC requirements informed
SRC-AGENTSKILLS-SPEChttps://agentskills.io/specificationMarkdown/frontmatter style, directory-as-package, progressive disclosure, fields/constraints/examples.Agent QC docs use concise entry pages, tables, examples, and deeper reference pages.
SRC-AGENTSKILLS-EVALhttps://agentskills.io/skill-creation/evaluating-skillsEval-driven iteration, clean-context runs, assertion grading, execution transcripts, human feedback.qcloop and eval gates require attempts, verifier feedback, rubrics, and evidence refs.
SRC-PLAYWRIGHT-CONFIGhttps://playwright.dev/docs/test-configuration and Context7 /microsoft/playwright.devprojects, webServer, retries, reporters, trace, screenshot, video, test isolation.WebUI/browser/desktop gates require trace/screenshot/video policy, browser project/device, console/network, and server startup evidence when relevant.
SRC-VITEST-DOCShttps://vitest.dev/guide/cli.html and Context7 /vitest-dev/vitestCLI run/watch, projects, reporter JSON/JUnit, coverage, browser mode, snapshots.JS projects map Vitest suites to deterministic, browser, contract, and report evidence lanes.
SRC-PYTEST-MARKERShttps://docs.pytest.org/en/stable/example/markers.html and Context7 /pytest-dev/pytestmarkers, -m selection, skip/xfail, parametrization, test routing.Python projects separate deterministic, integration, e2e, live, and slow suites with explicit selection and evidence.
SRC-MCP-TOOLShttps://modelcontextprotocol.io/specification/2025-11-25/server/toolstool declaration/protocol boundary.Tool/MCP gateway gates require declaration and invocation evidence, not only final text.
SRC-CODEX-ACTIONShttps://github.com/openai/codex/actionspublic workflow signal.Used only as external context; local repo inspection remains the case-study detail.
SRC-HERMES-GITHUBhttps://github.com/NousResearch/hermes-agentpublic project context.Used only for public project identity; local repo inspection supplies testing details.

Requirement traceability

Requirement areaPrimary sources
Surface evidence must link visible frame to runtime factsSRC-AGENTUI-BEST-PRACTICES, SRC-AGENTUI-FLOW, SRC-CODEX-LOCAL, SRC-OPENCLAW-LOCAL, SRC-HERMES-LOCAL
Expanded acceptance scenariosSRC-AGENTUI-ACCEPTANCE, SRC-CODEX-LOCAL, SRC-OPENCLAW-LOCAL, SRC-HERMES-LOCAL
TUI evidenceSRC-CODEX-LOCAL, SRC-CLAUDECODE-LOCAL, SRC-HERMES-LOCAL
WebUI/browser evidenceSRC-PLAYWRIGHT-CONFIG, SRC-VITEST-DOCS, SRC-OPENCLAW-LOCAL, SRC-HERMES-LOCAL
Python suite routingSRC-PYTEST-MARKERS, SRC-HERMES-LOCAL
Live provider separationSRC-OPENCLAW-LOCAL, SRC-HERMES-LOCAL
Scheduler/background gatesSRC-HERMES-LOCAL, SRC-AGENTUI-ACCEPTANCE
Release/distribution gatesSRC-CODEX-LOCAL, SRC-OPENCLAW-LOCAL, SRC-HERMES-LOCAL
Progressive documentation styleSRC-AGENTSKILLS-SPEC, SRC-AGENTKNOWLEDGE-SPEC, SRC-AGENTUI-BEST-PRACTICES
qcloop/eval evidence loopSRC-AGENTSKILLS-EVAL, SRC-OPENCLAW-LOCAL

Draft standard for evidence-driven quality control of Agent projects.