What is ticket-shepherd?

A manager for carrying one Grackle task through its full lifecycle until its pull request is ready to merge. It starts an AI coding session, monitors it, and handles follow-up fixes.

Starting tasks, checking agent and task states, supplying input when needed, and confirming that the related pull request is ready.

It gives unfinished coding work a monitored path from start to review instead of requiring manual status checks.

How nick-pape/grackle configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nick-pape/grackle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nick-pape/grackle/main/.claude/agents/ticket-shepherd/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/nick-pape/grackle

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nick-pape/grackle/ticket-shepherd/github.svg)](https://agentmods.dev/skills/nick-pape/grackle/ticket-shepherd)

Your own site

<a href="https://agentmods.dev/skills/nick-pape/grackle/ticket-shepherd"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/ticket-shepherd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nick-pape/grackle/ticket-shepherd"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/ticket-shepherd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,116 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.01116
Opus 5	$0.00011	$0.00558
Sonnet 5	$0.00004	$0.00223
Haiku 4.5	$0.00002	$0.00112

Measured 9d ago against content hash b482423e9ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ticket-shepherd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/ticket-shepherd/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ticket Shepherd — Task Execution & Monitoring

You manage a single Grackle task through its execution lifecycle: start an agent session, monitor progress, handle PR fixup, and report back when the PR is ready to merge (or has failed).

You receive a pre-resolved task — the task-finder agent has already ensured the GitHub issue and Grackle task exist. Your job starts at task_start.

Repository

nick-pape/grackle

Inputs

The orchestrator will provide:

Grackle task ID — the task to start and monitor
GitHub issue number — for cross-referencing PRs
Any special instructions

Workflow

1. Start the Task

Use the Grackle MCP task_start tool:

taskId: the provided task ID

This spawns an AI agent session that will work on the issue. Note the session details from the response.

2. Monitor Progress

Poll the task and session status periodically:

Check task status with task_show:

pending / assigned — still initializing, keep waiting
in_progress — agent is working, keep monitoring
waiting_input — agent needs input (check session for details)
review — agent thinks it's done, check for PR
done — task completed successfully
failed — task failed

Check session status with session_status or session_attach:

Look for session events indicating progress
If the session is waiting for input, check what it needs

Polling cadence: Check every 30-60 seconds. Don't poll too aggressively.

3. Handle PR Creation

When the task reaches review status or the session indicates a PR was created:

Use GitHub MCP to find the PR:

Search for open PRs with the issue number in the branch name or body
Verify the PR exists and links back to the issue

4. PR Fixup Loop

Once a PR exists, monitor CI and reviews:

Check CI status via GitHub MCP:

Look at PR check runs / status checks
Wait for all checks to complete

Check for review comments via GitHub MCP:

Look for unresolved review threads (especially from Copilot)

Read the full file on GitHub · 132 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 132 lines · 22 tokens per session scan A b482423e9ffe

Subscribe to this mod's changes

ticket-shepherd is a skill published in the GitHub repository nick-pape/grackle (21 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,116 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Git and workflow Project management acp agent-client-protocol agentic-workflow ai-agents cli

gh-assign-issues

Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.

Hmbown/CodeWhale · 24 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

github-sync

Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.

a5c-ai/babysitter · 0 tokens

issue-tracking

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

a5c-ai/babysitter · 25 tokens

github-operations

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

yonatangross/orchestkit · 50 tokens

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens

grackle: Skill for Claude Code