Skip to content
cccskills
FreePublished on GitHub

round-verification

Assess a completed execution round from supplied review, integration, change promotion, and verification records. Check for missing or conflicting evidence and return a script-readable result with audit details, without running tools or modifying code.

OriginalShow the original description

Verify integrated round evidence and return a machine-readable round result for script import.

See how to install

Good for

  • Auditing evidence after integration and change promotion
  • Checking review records against integrated changes
  • Detecting missing verification or cleanup evidence
  • Returning round decisions for script import

Files included (1)

  • SKILL.md1.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Round Verification

Use this skill after controller-owned node review, integration, promotion, and project-root verification have produced one compact round evidence packet.

Workflow

  1. Read the task and verification refs, every required compact node-review record, integration order/digest/tests, promotion or rollback evidence, project-root verification evidence, authority checks, and pre-review cleanup/release evidence. The current Round Reviewer may be the sole active dynamic agent; its final release is a controller-owned post-reply gate.
  2. Reject missing node review, reviewed-tree mismatch, integration drift, scope violation, hidden fallback, partial promoted delta, rollback drift, missing project-root checks, or unproven cleanup.
  3. Return exactly one machine-readable result line as the first non-empty line of the reply.
round result: pass|partial|replan_required|blocked

Do not write any preamble, heading, Markdown fence, bullet, quote, or backtick before or around that first line. Put evidence and audit details after it. Do not run tests, tools, shell commands, CCB commands, or workflow wrappers before producing the first line; verify from the evidence already supplied. If the evidence is insufficient, start with round result: blocked. A later round result: pass after prose is invalid and will be blocked by the runner.

Boundaries

  • Do not fix code.
  • Do not run tests or tools.
  • Do not change product scope.
  • Do not infer pass without evidence.
  • Do not submit downstream asks or mark the task or round done.
  • Do not directly edit authoritative CCB state or runtime files.
  • Provider and model selection remain project configuration concerns. This RolePack is provider-neutral and must not assume a specific provider.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

ask

FreeSummary

Delegate work or ask questions through CCB agents, choosing whether you need a brief answer, a preserved full response, or no success report. Select request options according to task dependencies and whether exact input must be retained.

  • Delegate a task to another CCB agent
  • Request only key findings from a consultation
  • Preserve exact logs or a full written response
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

ask

FreeSummary

Send work requests to another connected CCB agent with ask. Choose options according to whether the current task depends on the result or the work is independent, with terminal results routed through the existing request chain.

  • Delegate a concrete task to another agent
  • Request a result needed to finish the current task
  • Submit independent work whose successful result is not needed
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

ask

FreeSummary

Send questions or hand off work to another agent managed by CCB. Choose whether you need a short answer, a summary, or preserved full text, and distinguish independent tasks from tasks that require a reply.

  • Consulting a named agent
  • Handing off independent work
  • Preserving logs and detailed reports
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

Submit implemented and verified work to its assigned Reviewer, the agent responsible for checking it. Follow a bounded review and repair process, and report completion only after approval, or return a blocked or rework outcome.

  • Submitting implemented work for review
  • Applying requested repairs and resubmitting
  • Requiring review approval before completion
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

Execute one clearly scoped CCB task assigned by an orchestrator, the agent coordinating the workflow. Report a single outcome alongside changed files, commands, verification evidence, and unresolved blockers while leaving workflow authority unchanged.

  • Execute one assigned work item
  • Report completion against acceptance criteria
  • Document blockers preventing task completion
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

Carry out one clearly scoped implementation or investigation task, verify the work where possible, and submit evidence to the assigned reviewer. Reports changed paths, verification results, and blockers while preserving controller authority.

  • Implementing a change within assigned file paths
  • Investigating a narrowly defined issue
  • Submitting verification evidence to an assigned reviewer
SeemSeam/claude_codex_bridge3.6KUpdated Oct 22, 2026

See all skills by SeemSeam

Report a problem with this skill