issues-agent

A coding-agent connection to Issues, a ticket-tracking system for projects and work items. It can use either a personal API token or a service-account token through MCP or REST.

In plain words
What is it for?
Use it to list projects, search and inspect tickets, update fields, move tickets through workflow stages, and add comments.
Why use it?
It keeps ticket details, workflow changes, field updates, and comments available to the agent without switching to the tracker manually.

Skill for Claude CodeCodexCursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vepo/issues/issues-agent
Any agent
npx skills add vepo/issues --skill issues-agent
Clone the repo
git clone --depth 1 https://github.com/vepo/issues

Made for: Claude Code, Codex, Cursor.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00472
Opus 5 $0.00024 $0.00236
Sonnet 5 $0.00010 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 2d ago against content hash b43911da0854, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issues-agent 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 2d 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.

.cursor/skills/issues-agent/SKILL.md · 60 lines

What it actually says

Issues agent (MCP)

Backup skill for coding agents. Prefer in-app Conectar agente at /account/settings for paste-ready config.

Auth

Token Prefix Scope
Personal API token (PAT) iss_pat_… Acts as the user
Service account token iss_sat_… Member-aligned powers on one project

Send Authorization: Bearer <token> to Issues /api and to the MCP server (MCP forwards the same header).

Create PAT: Account → Tokens de API / Conectar agente.
Create SA: /projects/:projectId/service-accounts (PM/admin).

MCP tools (issues-mcp)

Separate Quarkus app — see issues-mcp/README.md. Default local URL: http://localhost:8082/mcp.

Tool Purpose
list_projects List viewable projects
search_tickets Search tickets
get_ticket_context Detail + transitions + in-scope custom fields
update_ticket Update fields
move_ticket Workflow transition
add_comment Add comment

Prefer get_ticket_context before mutating a ticket.

Cursor snippet

{
  "mcpServers": {
    "issues": {
      "url": "http://localhost:8082/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_TOKEN>"
      }
    }
  }
}

Or call GET /api/agent/setup-config?preset=cursor while logged in (uses issues.mcp-public-base-url).

Attribution

Mutations via API token set via_agent; ticket Atividade shows Agente em nome de <nome> (user or service-account display name).

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. 2d ago First seen · 60 lines · 48 tokens per session scan A b43911da0854

Subscribe to this mod's changes

issues-agent is a skill published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 472 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

agent-upkeep

Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…

NVIDIA/elements · 115 tokens

issue-tracker-ingestion

Pull issue/PR/ticket details from Jira, GitHub Issues, Linear, or Azure Boards via MCP into 01-spec.md ## Source. Use at the start of /spec whenever the user references an external ticket.

loiane/specs-driven-development-spring-angular · 53 tokens

openspec-apply-change

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

radix-ng/primitives · 31 tokens

openspec-archive-change

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

radix-ng/primitives · 31 tokens

kanera

Use Kanera MCP tools to search product guidance and discover, inspect, summarize, triage, create, or update project work. Trigger for requests about Kanera behavior, workspaces, boards, cards, standups, notes, comments, checklists, labels, custom fields, due dates, or project status.

happendev/Kanera · 66 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens