cvg-build-loop
Orchestrate a monitored implementation loop where a worker implements the plan and independent code review with focused rechecks gates completion. Use when the…
Handle plan-review blocker findings returned to the planner session. Validate feedback, revise plan-owned artifacts, or pause dependent work on missing decisions.
$ npx -y skills add gomilesf/convergo --skill cvg-plan-review-feedback --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cvg-plan-review-feedbackContext preview
The summary Claude sees to decide when to auto-load this skill.
Handle plan-review blocker findings returned to the planner session. Validate feedback, revise plan-owned artifacts, or pause dependent work on missing decisions.
name: cvg-plan-review-feedback description: "Handle plan-review blocker findings returned to the planner session. Validate feedback, revise plan-owned artifacts, or pause dependent work on missing decisions."
Use this skill in the planner session after a plan reviewer returns blocker findings.
The input is the reviewer blocker findings appended to the prompt, plus the original planning goal, source prompt, current plan, behavior contract if present, and relevant codebase evidence.
Do not treat reviewer findings as an edit list. First decide whether each finding is valid under the accepted goal and current code reality, then revise only plan-owned artifacts.
If the task context provides no coordination channel (standalone use), the current conversation is the channel. Ask only for a material unresolved decision; continue independent authorized work.
Read:
Recheck the original outcome, non-goals, authorized changes and current product constraints before treating plan text as a requirement. A contract gap blocks only when it prevents required behavior or critical verification. Use the orchestrator's evidence-based adjudications as input, retaining the original finding and explaining any disagreement or new evidence.
For materially added mechanisms, ask what required outcome or concrete constraint fails if they are removed. Consider deleting the cause or reusing existing behavior before prescribing more coordination, recovery, or guards. A counterfactual explanation is not an executed ablation experiment. Run an isolated removal experiment only when uncertainty could change the choice and it is within your role; preserve the baseline and verify affected behavior. Keep necessary privacy, integrity and failure protection even for rare schedules. Use existing finding fields to explain the consequence and smallest effective change; do not add a separate complexity report or demand a deletion quota.
For each finding, decide whether it is:
matrix cell, ownership boundary, or verification gate.
the plan or contract failed to capture it.
defines the behavior clearly enough to proceed.
plan or code evidence after re-reading the relevant context.
the accepted goal, or asks for work outside the agreed scope.
For valid plan gaps and source-backed contract gaps:
gates as needed,
For decision-required contract gaps:
source-backed details without repeating user approval,
For reviewer clarification:
For invalid or out-of-scope findings:
Before editing, write a compact intake summary:
Plan review feedback intake: 1. Finding: <reviewer finding id or short quote> Decision: <valid plan gap / source-backed contract gap / decision-required contract gap / clarification needed / invalid or out of scope> Action: <plan edit / contract edit / stop for decision / ask reviewer / no change> Evidence: <plan/code reference>
After acting, report:
Plan → review → build loops for coding agents — that actually terminate. Agent-written code needs review, and agent review needs a loop: find issues, fix them, review again.
Repo: gomilesf/convergo
Orchestrate a monitored implementation loop where a worker implements the plan and independent code review with focused rechecks gates completion. Use when the…
Handle code-review blocker findings returned to the worker session. Validate feedback, repair implementation-owned issues, or pause dependent work on plan and…
Review implementation against the plan and contract. Distinguish code bugs from contract gaps. Bounded convergence.
Orchestrate the build loop with split engines - Codex CLI sessions implement and take every first-pass review round while a high-taste Claude design model…
Orchestrate the plan loop with split engines - a high-taste Claude design model drafts and revises the plan while Codex CLI sessions gate it as fresh plan…
Orchestrate real specialist sessions as one monitored multi-agent workflow. Use when the user asks to coordinate or supervise multiple agent sessions, planning…