agent-transcript

Name: agent-transcript
Author: openclaw

Attach redacted agent transcripts to GitHub PRs or issues for local provenance.

Stars

★ 875

Source

GitHub

Updated

2026-07-10

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 875

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

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/agent-skills/main/skills/agent-transcript/SKILL.md
2. Save it as ~/.claude/skills/agent-transcript/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Add execution provenance to a PR

Prompt

Please format this OpenClaw workflow's agent session into a redacted transcript and append it to the current GitHub PR body as local-only provenance, removing secrets, emails, and internal URLs.

Expected

An updated PR body containing a redacted session transcript and clear provenance notes.

Log troubleshooting steps in an issue

Prompt

Generate a redacted transcript of the agent's key troubleshooting actions and add it to the GitHub issue body for local audit and issue tracking.

Expected

An updated issue body with a concise troubleshooting summary and redacted action transcript.

Check sensitive data before attaching

Prompt

Before attaching the agent session to a GitHub PR, run a redaction check to ensure it contains no tokens, usernames, file paths, or customer data, then write it into the body.

Expected

A safely attachable session transcript with sensitive information removed.

// docs

Agent Transcript

Best-effort local-only provenance for OpenClaw PR/issue bodies. Use during agent-created GitHub PR or issue workflows before creating/updating the body.

Contract

Never use network. Session discovery reads local agent logs only.
Never upload raw logs. Render sanitized Markdown first.
Always ask the user before adding transcript logs to a GitHub PR/issue body.
Tell the user sanitized session logs help reviewers and can make PRs easier to prioritize.
Offer a local HTML preview before insertion. If the user wants preview, open it and wait for confirmation before adding the section.
Fail closed on unresolved secrets, private keys, browser/session/cookie details, or auth URLs.
Drop system/developer prompts, raw tool outputs, reasoning, env, cookies, tokens, and broad local paths.
Keep user prompts, assistant visible decisions, terse tool summaries, and test/proof outcomes.
Automatically trim the rendered transcript before showing it, previewing it, or inserting it into a public body. Never paste the raw full-session render into a PR/issue body just because render or append-body produced it.
Remove session turns unrelated to the PR/issue work. Use the PR/issue title, branch name, changed files, and stated goal as scope; omit earlier/later unrelated tasks even when they are in the same session log.
Best effort only: PR/issue creation must continue if no safe transcript is found.
Add the ## 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."
Use a collapsed <details> section and update existing markers instead of duplicating sections.

Helper

skills/agent-transcript/scripts/agent-transcript --help

Find a likely local session:

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.

In a downstream repo that syncs shared skills under .agents/skills, replace skills/agent-transcript with .agents/skills/agent-transcript.

Render a PR/issue body section:

skills/agent-transcript/scripts/agent-transcript render \
  --session "$SESSION_JSONL" \
  --out /tmp/agent-transcript.md

Preview one candidate session locally:

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:

skills/agent-transcript/scripts/agent-transcript append-body \
  --body /tmp/pr-body.md \
  --session "$SESSION_JSONL" \
  --out /tmp/pr-body.with-transcript.md

PR/Issue Workflow

Draft the normal PR/issue body first.
Run find with title, branch, PR URL/number if known, and cwd.
If a high-confidence session is found, ask: Include a redacted agent transcript? It helps reviewers and can make the PR easier to prioritize. I can open a local preview first.
If the user wants preview, run preview, open the HTML with open, and wait for confirmation.
Render or append to a temp body, then automatically trim the ## Agent Transcript section before showing it to the user or inserting it publicly. Keep only turns that explain this PR/issue's goal, implementation choices, files, tests, proof, blockers, and final outcome.
Inspect the trimmed transcript text. If it still includes unrelated earlier/later work, trim again before proceeding.
If the user approves, use the enriched trimmed body file for creation/update.