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 skills/cboone/agent-harness-plugins/create-worktree-from-issuenpx skills add cboone/agent-harness-plugins --skill create-worktree-from-issuegit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/skills/cboone/agent-harness-plugins/create-worktree-from-issue)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/create-worktree-from-issue"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/create-worktree-from-issue.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 | $0.00109 | $0.01588 |
| Opus 5 | $0.00055 | $0.00794 |
| Sonnet 5 | $0.00022 | $0.00318 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
create-worktree-from-issue 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Worktree from Issue
Find a GitHub issue and create a dedicated worktree + tmux window via workmux add.
Workflow
1. Find the Issue
The user provides either an issue number or descriptive text.
By number:
gh issue view NUMBER --json number,title,labels,body,state
By text (fuzzy search):
gh issue list --search "USER_TEXT" --state all --json number,title,labels,state --limit 10
If the search returns exactly one result, proceed automatically with that issue without asking for additional confirmation.
If the search returns multiple results, present them to the user and ask which one to use.
If no results, try broadening the search or ask the user to refine their query.
2. Mark Issue In Progress
If the issue is open, signal that work is starting. Skip this step for closed issues.
Self-assign:
gh issue edit NUMBER --add-assignee @me
Ensure the label exists, then add it:
gh label create "in progress" --description "Work is actively being done" --color FBCA04 2> /dev/null || true
gh issue edit NUMBER --add-label "in progress"
The gh label create command is safe to run even if the label already exists — 2>/dev/null suppresses the "already exists" error and || true ensures a zero exit code so the subsequent command always runs. This ensures the label is available before gh issue edit --add-label attempts to use it, since gh does not auto-create labels.
Self-assignment is idempotent — safe to re-run if the assignee already exists.
If any command fails, warn the user but continue with worktree creation. Status marking is best-effort and must never block the primary workflow.
The "in progress" label is intentionally retained beyond worktree creation and local implementation. It represents active issue lifecycle state until the related pull request is merged or the user explicitly abandons the effort. Do not remove it as part of creating the worktree.
3. Build the Branch Name
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.
- 3d ago First seen · 135 lines · 109 tokens per session scan A 5c6491b88bfc
create-worktree-from-issue is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,588 once invoked, about $0.0005 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.
Other skills, from other repositories
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
aidd-context:04:mermaid
Generate high-quality Mermaid diagrams from markdown content using a structured plan-validate workflow.
aidd-dev:06:refactor
Optimize code for performance and fix security vulnerabilities following OWASP guidelines.
aidd-context:03:context-generate
Generate Claude Code context artifacts - skills (router-based: SKILL.md + atomic testable actions + minimal evals), agents, and rules. Use when the user wants to create, refactor, add or remove actions in a skill, migrate a slash command into a skill, or generate a new agent or rule. Do NOT use for editing a single…