Skip to content

hashgraph-online/awesome-codex-plugins / plugins/boshu2/agentops/skills/research

research

Verified

Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.

scripts/claim-audit/validate-output.sh

View on GitHub
#!/usr/bin/env bash
set -euo pipefail

if [[ $# -ne 1 || ! -f "$1" ]]; then
  echo "usage: $0 <reality-check-report.json>" >&2
  exit 2
fi

if ! command -v jq >/dev/null 2>&1; then
  echo "reality-check-report validator requires jq, which is not on PATH" >&2
  exit 2
fi

# coverage is the per-item ledger: at least one row, and every confirmed or gap
# row cites evidence. An unverifiable row may name what would settle it.
jq -e '
  def text: type == "string" and length > 0;
  ((keys - ["schema_version","claim","findings","coverage"]) | length == 0)
  and .schema_version == "reality-check-report.v1"
  and (.claim | text)
  and (.findings
    | type == "array" and length > 0
    and all(.[];
      ((keys - ["category","statement","evidence"]) | length == 0)
      and (.category == "confirmed" or .category == "gap"
        or .category == "incomplete-evidence" or .category == "changed-assumption")
      and (.statement | text)
      and (.evidence | type == "array" and length > 0 and all(.[]; text))))
  and (.coverage
    | type == "array" and length > 0
    and all(.[];
      . as $row
      | ((keys - ["goal","disposition","evidence"]) | length == 0)
      and ($row.goal | text)
      and ($row.disposition == "confirmed" or $row.disposition == "gap" or $row.disposition == "unverifiable")
      and (if $row.disposition == "unverifiable"
           then ((has("evidence") | not) or ($row.evidence | type == "array" and all(.[]; text)))
           else ($row.evidence | type == "array" and length > 0 and all(.[]; text)) end)))
' "$1" >/dev/null || {
  echo "invalid reality-check-report.v1 artifact: $1" >&2
  exit 1
}

echo "valid reality-check-report.v1: $1"
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall