gh-issue-labels

gh-issue-labels is a skill for Claude Code from skyfox675/agents-skills. It costs 179 tokens per session (4,340 once invoked), scanned A, original, MIT.

A label system for controlling how AI agents handle GitHub issues. Labels are visible, persistent markers that can hold an issue, assign a model, mark it claimed, or control pull-request handling.

In plain words
What is it for?
Use it to define and interpret labels such as agent-model, agent-effort, agent-claimed, do-not-dispatch, and do-not-rebase.
Why use it?
It gives multiple operators a shared and auditable way to guide automated dispatch. The instructions remain attached to the issue instead of being lost in chat.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Good fit Use it to define and interpret labels such as agent-model, agent-effort, agent-claimed, do-not-dispatch, and do-not-rebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skyfox675/agents-skills/gh-issue-labels
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.

Any agent
npx skills add skyfox675/agents-skills --skill gh-issue-labels
Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

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 gh-issue-labels

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-labels/github.svg)](https://agentmods.dev/skills/skyfox675/agents-skills/gh-issue-labels)
Your own site
<a href="https://agentmods.dev/skills/skyfox675/agents-skills/gh-issue-labels"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-labels/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 gh-issue-labels

Your own site · 80×15
<a href="https://agentmods.dev/skills/skyfox675/agents-skills/gh-issue-labels"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-labels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,340 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00179 $0.04340
Opus 5 $0.00089 $0.02170
Sonnet 5 $0.00036 $0.00868
Haiku 4.5 $0.00018 $0.00434

Measured 7d ago against content hash 7808e9512bc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gh-issue-labels 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/bootstrap-labels.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/gh-issue-labels/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Labels

A small set of GitHub labels forms the persistent, auditable control plane between human operators and orchestrating agents. Labels survive across sessions, are visible to every concurrent operator, and are machine-readable in pre-dispatch filters — properties that chat instructions and issue comments do not have. This skill defines the full taxonomy: what each label means, who sets it, who consumes it, and the resolution rules when signals conflict.

Companion skills: issue selection and the dispatch brief live in the dispatching-subagents skill; the claim/lock/release protocol behind agent-claimed lives in the gh-issue-locking skill; the slot loop that reads these labels every round lives in the orchestrating-slots skill; PR-side mechanics behind do-not-rebase live in the driving-prs-to-merge skill. The Jira equivalent (Jira fields/labels instead of GitHub labels) is the jira-issue-fields skill.

Project bindings

Adopting projects define these values in their own CLAUDE.md. Refer to them by placeholder everywhere below.

Binding Meaning Example
<workhorse-model> Default model for all code-writing dispatches sonnet
<cheap-model> Model for narrow mechanical tasks only — deliberately has NO label haiku
<premium-models> Operator-gated high-attention models (one label each) opus, fable
<integration-branch> Branch PRs target (affects close-on-merge, see gh-issue-locking) dev
<repo-slug> org/repo for --repo flags in label REST calls; see gh-issue-filing for the canonical definition acme/widgets
<auto-rebase-automation> Whatever workflow/bot rebases open PRs onto <integration-branch> a scheduled auto-rebase workflow
<operator-logins> GitHub logins of humans running orchestrators concurrently — resolved at runtime; assignees are set via gh api user --jq .login resolve dynamically
<lock-comment-format> Parseable lock-comment marker paired with agent-claimed — full spec in gh-issue-locking <!-- claude-lock: ... -->

Read the full file on GitHub · 302 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 302 lines · 179 tokens per session scan A 7808e9512bc8

Subscribe to this mod's changes

gh-issue-labels is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 179 tokens to every session and 4,340 once invoked, about $0.0009 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 2026-09-03.