backlogit

Time-boxed investigation of a technical question, feasibility study, or proof-of-concept — produces a findings artifact with a recommendation and optional backlog linkage

Time-boxed investigation of a technical question, feasibility study, or proof-of-concept — produces a findings artifact with a recommendation and optional backlog linkage

Usage: Build feature {task-id} with harness {harness-cmd}. Implements a requested feature by continuously looping a fast worker agent against a strict, passing-import but failing test harness until success is achieved.

Review and maintain institutional learnings in docs/compound/ so the compound library stays accurate, deduplicated, and evidence-backed

Risk-triggered plan reinforcement that deepens verification, rollback, and guardrail detail before plan review

Manages the full PR lifecycle: creation, review comment handling, CI remediation, and user-approved merge

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

Scaffolds compilable but failing test harnesses for feature and chore tasks

Autonomous iterative experimentation loop. Defines a measurable goal, establishes a baseline, then iterates modify→commit→measure→keep/revert until the goal is met or the budget is exhausted. Persists a TSV experiment log under the configured results directory.

Multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into work items.

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status before or after backlogit_ship_shipment runs.

Usage: Build feature {task-id} with harness {harness-cmd}. Implements a requested feature by continuously looping a fast worker agent against a strict, passing-import but failing test harness until success is achieved.

Scaffolds compilable but failing Go test harnesses for backlogit tasks

Decomposes a reviewed implementation plan into backlogit feature/task/subtask hierarchy

Multi-model, multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into backlogit work items.

Manages the full PR lifecycle: creation, Copilot comment handling, CI remediation, and user-approved merge

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

Interactive safety workflows for elevated-risk work — careful, freeze-scope, investigate-first, and explicit action-risk/result tracking

Produce release-readiness, monitoring, rollback, and feedback artifacts that close the loop after implementation and verification - Brought to you by microsoft/hve-core

Validate affected runtime surfaces after build and CI using manual, API, or browser-backed verification

Acquire and release file-level locks to prevent concurrent modifications during multi-agent or human+agent workflows

Dynamic skill discovery: search available skills by keyword instead of loading all skill definitions into the system prompt

Transform backlogit deliberation artifacts, feature descriptions, or research documents into structured implementation plans grounded in repo patterns and research. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a deliberate session is ready for technical planning.

Usage: Fix CI. Detects CI pipeline failures and GitHub Copilot review comments on the current branch's PR, reproduces and fixes errors locally, addresses review comments, runs all CI gates, then pushes and polls until the pipeline passes and comments are resolved.

Explore requirements and approaches through collaborative dialogue, capture the result in the backlogit stash, and create a linked deliberation artifact for later planning and harvest. Use when the user says 'deliberate', 'explore', 'think this through', 'what should we build', or 'help me think through'.

Scan .copilot-tracking/ for stale or oversized tracking artifacts, produce compacted summaries, and archive originals. Use when tracking files accumulate beyond thresholds that degrade agent context quality.

Document a recently solved problem to compound institutional knowledge. Captures solutions in docs/compound/ with searchable YAML frontmatter for the learnings-researcher. Use after fixing bugs, resolving build issues, or discovering gotchas.