mcp-skillset: Agent for Claude Code

.claude/agents/ticketing.md

ticketing is an agent for Claude Code from bobmatnyc/mcp-skillset. It costs 114 tokens per session (15,117 once invoked), scanned B, original, MIT.

An agent for creating and maintaining technical documentation, such as API references, user guides, and technical specifications. It also manages ticket tags while preserving tags supplied by a project manager.

In plain words
What is it for?
Use it to write or update technical documents and to organize related tickets with merged project and scope tags.
Why use it?
It helps keep documentation work organized and prevents important ticket labels from being replaced or ignored.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

This is bobmatnyc/mcp-skillset's own configuration. It tells Claude Code how to work on mcp-skillset itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-skillset configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobmatnyc/mcp-skillset. 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/bobmatnyc/mcp-skillset/main/.claude/agents/ticketing.md
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-skillset

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.

agentmods badge for ticketing

README.md
[![agentmods](https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/ticketing/github.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-skillset/ticketing)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/ticketing"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/ticketing/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.

agentmods 80×15 button for ticketing

Your own site · 80×15
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/ticketing"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/ticketing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 15,117 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.15117
Opus 5 $0.00057 $0.07558
Sonnet 5 $0.00023 $0.03023
Haiku 4.5 $0.00011 $0.01512

Measured 9d ago against content hash 404d61901b98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

ticketing scanned grade B with 1 finding 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

grep -q "mcp-ticketer" ~/.config/claude-mpm/mcp.json && echo "MCP available" || echo "Use aitrackdown"
.claude/agents/ticketing.md · 2,084 lines

How it starts

The opening of the file, as written. The whole thing — 2,084 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ticketing Agent

Intelligent ticket management with MCP-first architecture and script-based fallbacks.

Tag Preservation Protocol

PM-specified tags should be preserved to maintain delegation authority and ensure proper ticket organization. When the PM provides tags, they represent the project's organizational structure and filtering requirements.

Tag Handling Rules:

  1. generally check for PM-provided tags first:
pm_tags = delegation_context.get('tags', [])
  1. MERGE tags, avoid replace:
# Merge to preserve delegation chain while adding context
final_tags = pm_tags + scope_tags

# Avoid: Replace PM tags
tags = ["hardcoded", "scope-tags"] # This breaks delegation chain
  1. Disable auto-detection when PM provides tags:
auto_detect_labels = False if pm_tags else True
  1. Tag Priority Matrix:
  • Highest Priority: PM-specified tags (generally preserve)
  • Medium Priority: Scope tags (merge with PM tags)
  • Lowest Priority: Auto-detected tags (ONLY if PM provides none)

Common Mistakes to Avoid

  • Replacing PM tags with hardcoded tags
  • Enabling auto_detect_labels when PM provides tags
  • Ignoring PM-specified tags
  • Overriding PM tags with scope tags

Recommended Pattern

pm_tags = delegation.get('tags', [])
scope_tags = ["in-scope", "subtask"] if is_in_scope else []
final_tags = pm_tags + scope_tags # Merging preserves delegation traceability
auto_detect = False if pm_tags else True

Pre-Creation Validation Function:

Before creating ANY ticket, validate tag handling:

def validate_tags(pm_tags, final_tags, auto_detect):
\"\"\"Ensure PM tags are preserved correctly\"\"\"

# Check 1: All PM tags should be in final tags
for tag in pm_tags:
assert tag in final_tags, f"PM tag '{tag}' was dropped!"

# Check 2: Auto-detection should be disabled if PM provided tags
if pm_tags:
assert auto_detect == False, "Auto-detection enabled with PM tags!"

# Check 3: Final tags should not be empty if PM provided tags
if pm_tags:
assert len(final_tags) > 0, "Final tags empty despite PM tags!"

return True

Read the full file on GitHub · 2,084 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.

  1. 9d ago First seen · 2,084 lines · 114 tokens per session scan B 404d61901b98

Subscribe to this mod's changes

ticketing is an agent published in the GitHub repository bobmatnyc/mcp-skillset (20 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 15,117 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.