issue-orchestrator

issue-orchestrator is a skill for Claude Code, Codex from jonathanung/strike. It costs 71 tokens per session (1,634 once invoked), scanned A, original, Apache-2.0.

A coordinator for moving open GitHub issues toward merged changes using separate Git workspaces and issue-handler agents. It reads dependency, conflict, wave, and priority information from issue headers to decide what can run together.

In plain words
What is it for?
Use it to inspect the issue board, group work into waves, dispatch independent issues, avoid conflicting tasks, and track which closed issues unlock others.
Why use it?
It reduces scheduling mistakes when several issues share files or depend on earlier work. It also keeps bug fixes ahead of feature work within the same wave.

Skill for Claude CodeCodex

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/jonathanung/strike/issue-orchestrator
Any agent
npx skills add jonathanung/strike --skill issue-orchestrator
Clone the repo
git clone --depth 1 https://github.com/jonathanung/strike

Made for: Claude Code, Codex.

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 issue-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/jonathanung/strike/issue-orchestrator.svg)](https://agentmods.dev/skills/jonathanung/strike/issue-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/jonathanung/strike/issue-orchestrator"><img src="https://agentmods.dev/badge/skills/jonathanung/strike/issue-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,634 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 $0.00071 $0.01634
Opus 5 $0.00036 $0.00817
Sonnet 5 $0.00014 $0.00327
Haiku 4.5 $0.00007 $0.00163

Measured 3d ago against content hash cc8db4d7a2a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-orchestrator 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 3d 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/skills/issue-orchestrator/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue orchestrator (strike-cli)

You coordinate many issues. You do not implement feature code in the primary checkout. Each shippable unit is owned by an issue-handler agent (or you acting as handler for a single issue) inside its own git worktree.

When to use

  • User asks to orchestrate / farm / drain open issues
  • User wants parallel agents on the backlog
  • After filing a wave of issues and wanting them driven to main

Source of truth

gh issue list --state open --limit 100
gh issue view N
gh pr list --state open
git fetch origin main
git worktree list

Issue body headers (machine-readable)

Issues should start with:

wave: N
depends: none | #a #b
blocks: none | #c #d
conflicts: none | #e #f
priority: bugs-first | feature
Field Meaning
wave Lower ships first. Wave 0 = bugs/tests baseline.
depends All listed issues must be CLOSED before start
conflicts Do not run in parallel with these (shared files / same agent)
blocks What this unlocks (scheduling hint)
priority bugs-first before feature within the same wave

Closed depends count as satisfied.

Missing headers: treat as wave: 99, depends: none, conflicts: none, priority: feature. Prefer issues that have proper headers. When farming, comment once on headerless issues asking for headers (or load issue-create-and-handle to refine) before parallel dispatch — do not guess large parallel graphs.

Suggested conflicts hotspots

Serialize (or mark mutual conflicts) when multiple issues touch:

  • internal/frontend/tui/app/_src/app/keymap*.go, default keybinds, internal/product/config/keybinds.go
  • internal/engine/turn.go / core turn loop
  • internal/tool/registry.go + defer/toolsearch wiring
  • internal/protocol event kind additions shared across frontends

Prefer explicit conflicts: #N on the issue over silent collision.

Sibling skills

Skill Role
issue-handler One issue → worktree → implement → test → PR → review-agent loop → CI → merge → cleanup
test-and-validate Verification report format + tiers
write-go-tests Tests when handler implements
smoke Product happy-path when user-visible
release Version tags (orchestrator does not cut releases unless asked)
tui-components TUI work inside a handler

Read the full file on GitHub · 158 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. 3d ago First seen · 158 lines · 71 tokens per session scan A cc8db4d7a2a1

Subscribe to this mod's changes

issue-orchestrator is a skill published in the GitHub repository jonathanung/strike (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,634 once invoked, about $0.0004 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

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

sap-transport-overview

System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…

arc-mcp/arc-1 · 106 tokens

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

pm-all

Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).

wei63w/pm-manager · 8 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens

finn-spec

Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.

finna/Finn-loop · 56 tokens