DataArt/artisyn-implementation-harness / skills/implementation-harness
implementation-harness
FlaggedInstall the portable AI-dev harness, rebuild its operational graph standalone, harvest project skill improvements into its canonical templates, package direct canonical edits into a portable bundle, or apply canonical updates to an existing project. Use /implementation-harness launch, /implementation-harness reindex-graph, or /implementation-harness patch harvest|prepare|apply.
canonical/skills/dev/scripts/constants.mjs
View on GitHub// Constants for the dev metrics CLI; no dependency on another flow.
/** Lifecycle this recorder owns; stat.json files from other lifecycles are rejected. */
export const LIFECYCLE = 'dev';
/** The lifecycle's stages, in flow order. */
export const STAGES = Object.freeze([
'context',
'ceremony',
'plan',
'implement',
'test',
'document',
'completion',
]);
/** Stage whose completion gates ticket completion. */
export const FINAL_STAGE = 'completion';
/** File names this recorder owns inside the ticket directory. */
export const FILES = Object.freeze({
stat: 'stat.json',
report: '2-report.md',
lock: '.dev-metrics.lock',
});
/** HTML comments delimiting the generated Stage Metrics block in the report file. */
export const STAGE_REPORT_MARKERS = Object.freeze({
start: '<!-- dev-metrics-stage:start -->',
end: '<!-- dev-metrics-stage:end -->',
});
/** HTML comments delimiting the generated Step Metrics block in the report file. */
export const STEP_REPORT_MARKERS = Object.freeze({
start: '<!-- dev-metrics-step:start -->',
end: '<!-- dev-metrics-step:end -->',
});
/** Pre-split marker pair from reports generated before the stage/step split; migrated in place by `report`. */
export const LEGACY_REPORT_MARKERS = Object.freeze({
start: '<!-- dev-metrics:start -->',
end: '<!-- dev-metrics:end -->',
});
/** Default work activity opened when each stage starts. */
export const ACTIVITIES_BY_STAGE = Object.freeze({
context: 'investigation',
ceremony: 'planning',
plan: 'planning',
implement: 'implementation',
test: 'verification',
document: 'documentation',
completion: 'documentation',
});
/** Allowed work-interval activities. */
export const ACTIVITIES = Object.freeze([
'investigation',
'planning',
'implementation',
'verification',
'review',
'documentation',
]);
/** Allowed wait-interval reasons. */
export const REASONS = Object.freeze([
'approval',
'user_input',
'external_dependency',
'environment',
]);
/** Allowed retry triggers for reopening a stage or step. */
export const TRIGGERS = Object.freeze([
'verification_failure',
'review_feedback',
'scope_change',
'reopened',
]);
/** Allowed `## Review Findings` Kind values. */
export const FINDING_KINDS = Object.freeze([
'deviation',
'bug',
'design',
'improve',
'security',
'performance',
'docs',
]);
/** Allowed `## Review Findings` Severity values. */
export const FINDING_SEVERITIES = Object.freeze(['critical', 'high', 'medium', 'low', 'info']);
/** Allowed `## Review Findings` Resolution values. */
export const FINDING_RESOLUTIONS = Object.freeze([
'open',
'fixed',
'accepted',
'tech-debt',
'doc-updated',
]);
/** Allowed `## Review Findings` Origin values (semicolon-separated per row). */
export const FINDING_ORIGINS = Object.freeze([
'plan-audit',
'implementation-review',
'pr-review',
'hld-audit',
'doc-consistency',
]);
/** Allowed `## Review Findings` Classification values. */
export const FINDING_CLASSIFICATIONS = Object.freeze([
'introduced',
'pre-existing',
'ruled-out',
'advisory',
]);
/** Allowed `## Review Findings` Deviation type values (only when Kind is `deviation`). */
export const FINDING_DEVIATION_TYPES = Object.freeze(['contradiction', 'extension', 'omission']);
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |