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.
npx agentmods add agents/joachimwedin/gh-issues-mcp/issue-trackergit clone --depth 1 https://github.com/joachimwedin/gh-issues-mcpWrote 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.
[](https://agentmods.dev/agents/joachimwedin/gh-issues-mcp/issue-tracker)<a href="https://agentmods.dev/agents/joachimwedin/gh-issues-mcp/issue-tracker"><img src="https://agentmods.dev/badge/agents/joachimwedin/gh-issues-mcp/issue-tracker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01489 |
| Opus 5 | $0.00000 | $0.00745 |
| Sonnet 5 | $0.00000 | $0.00298 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
issue-tracker 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue tracker: GitHub
Issues and PRDs for this repo live as GitHub issues. This repo dogfoods its
own server: use the gh-issues-mcp MCP tools for all issue operations.
The gh CLI is not a fallback — treat it as unavailable. If an operation
you need isn't covered by any tool below, that's a real gap in the server,
not something to route around: say so explicitly, and treat it as a
candidate for a new gh-issues-mcp tool (e.g. by filing an issue against
this repo) rather than improvising another way to do it.
Conventions
Every tool below (except list_repos) takes an optional repo param,
"owner/name", checked against the server's configured repo allowlist. Omit
it to target the server's default repo. list_repos() returns the full
allowlist plus each repo's effective label vocabulary — call it first when
you don't already know the target repo or its vocabulary.
This repo's tracker repo is joachimwedin/gh-issues-mcp (see CLAUDE.md).
Pass repo: "joachimwedin/gh-issues-mcp" explicitly on every call rather
than omitting it — the server's allowlist also includes other repos, and
its configured default may point at one of those instead.
- Discover repos:
list_repos()— no params; returns[{ repo, labelVocabulary }]for every repo in the allowlist. - Create an issue:
create_issue(title, body, labels?, repo?)— creates a new top-level issue. Iflabelsis given, only labels in the resolved repo's configured vocabulary are accepted — seedocs/agents/triage-labels.md. - Read an issue:
view_issue(number, repo?)— returns body, labels, full comment history, the issue's parent (if any, elsenull), and its sub-issues (if any, else[]) in one call. - List issues:
list_issues(state?, labels?, repo?)— PRs are excluded automatically, since this server treats issues, not PRs, as the triage surface. - Comment on an issue:
comment_issue(number, body, repo?). - Apply / remove labels:
edit_labels(number, add?, remove?, repo?). Only labels in the resolved repo's configured vocabulary are accepted — seedocs/agents/triage-labels.md. If a label you need isn't in the vocabulary, flag it as a gap (config or tool) rather than trying to force it another way. Unlike the other tools, its result is{ repo, labels }(the resolved repo and the issue's resulting label list), not a tagged issue object. - Close:
close_issue(number, comment, repo?)—commentis required, so an issue can never be closed without an explanation. - Create a sub-issue:
create_sub_issue(parent_number, title, body, repo?)— creates a new issue and links it to the parent via GitHub's sub-issues API in one call. Parent and child are always in the same repo. - Edit an issue:
edit_issue(number, title?, body?, repo?)— updates an existing issue's title and/or body. At least one oftitle/bodymust be given.
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.
- 4d ago First seen · 87 lines · 0 tokens per session scan A 0c9784d5b021
issue-tracker is an agent published in the GitHub repository joachimwedin/gh-issues-mcp (0 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,489 tokens. 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 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.