Automatically add redacted agent transcripts to GitHub PRs or issues.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "agent-transcript" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/agent-transcript/SKILL.md 2. Save it as ~/.claude/skills/agent-transcript/SKILL.md 3. Reload skills and tell me it's ready
Append an 'Agent Transcript' section to a GitHub PR body created by OpenClaw, and redact secrets, tokens, and sensitive paths.
The PR body includes a redacted agent transcript section for review and traceability.
When OpenClaw automatically creates a GitHub issue, add the agent action transcript to the body and hide credentials, emails, and internal links.
The issue body contains a clear redacted transcript so the team can understand the agent workflow.
Insert a standardized redacted transcript block into all OpenClaw-generated PRs and issues, keeping key steps while removing sensitive content.
All related PRs and issues include consistently formatted redacted audit transcripts.
Best-effort local-only provenance for OpenClaw PR/issue bodies. Use during agent-created GitHub PR or issue workflows before creating/updating the body.
## Agent Transcript section only when inserting a real transcript. Never add a placeholder transcript heading or text such as "A sanitized local transcript preview was generated but not included."<details> section and update existing markers instead of duplicating sections..agents/skills/agent-transcript/scripts/agent-transcript --help
Find a likely local session:
.agents/skills/agent-transcript/scripts/agent-transcript find \
--query "$PR_TITLE $BRANCH_OR_PR_URL" \
--cwd "$PWD" \
--since-days 14
find scans the newest 400 matching local JSONL logs by default across Codex, Claude, Pi, and OpenClaw agent sessions. Use --max-files N for a wider local search.
Render a PR/issue body section:
.agents/skills/agent-transcript/scripts/agent-transcript render \
--session "$SESSION_JSONL" \
--out /tmp/agent-transcript.md
Preview one candidate session locally:
.agents/skills/agent-transcript/scripts/agent-transcript preview \
--session "$SESSION_JSONL" \
--out /tmp/agent-transcript-preview.html
open /tmp/agent-transcript-preview.html
Append/update a body file before gh pr create --body-file or connector PR creation:
.agents/skills/agent-transcript/scripts/agent-transcript append-body \
--body /tmp/pr-body.md \
--session "$SESSION_JSONL" \
--out /tmp/pr-body.with-transcript.md
find with title, branch, PR URL/number if known, and cwd.Include a redacted agent transcript? It helps reviewers and can make the PR easier to prioritize. I can open a local preview first.preview, open the HTML with open, and wait for confirmation.append-body.For manual audits across many PR/session candidates, create a local HTML preview from a local JSON file. This is for maintainers only and is not part of the PR/issue workflow:
.agents/skills/agent-transcript/scripts/agent-transcript html \
--prs /tmp/recent-prs.json \
--out /tmp/agent-transcript-preview.html
Create, search, and manage Bear notes on macOS via grizzly CLI.
Run or recover OpenClaw macOS signing, notarization, and release promotion.
Search and analyze Slack archives, count threads, and support repo workflows.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Build quick throwaway prototypes to validate options and deliver a verdict.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Attach redacted agent transcripts to GitHub PRs or issues for local provenance.
Convert Lighthouse audits into fix packs for coding agents.
Add fail-closed quality gates and hash-chained audit receipts to AI agent workflows.
Create tamper-evident audit trails and observability records for AI agents.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Analyze local-first AI agent CLI usage patterns and invocation data.