shift: Skill for Claude Code

.agents/skills/issue/SKILL.md

issue is a skill for Claude Code, Codex from shift-editor/shift. It costs 64 tokens per session (1,057 once invoked), scanned A, original, Apache-2.0.

A set of rules for finding, creating, updating, and searching GitHub issues in a software project. It also defines how issues connect to pull requests.

In plain words
What is it for?
Use it when triaging work, filing an issue, updating its status, or checking whether substantial work needs an issue first.
Why use it?
It helps prevent duplicate issues and keeps bug reports or work requests clear enough to plan and review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is shift-editor/shift's own configuration. It tells Claude Code and Codex how to work on shift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shift configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shift-editor/shift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shift-editor/shift/main/.agents/skills/issue/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shift-editor/shift

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/shift-editor/shift/issue"><img src="https://agentmods.dev/badge/skills/shift-editor/shift/issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,057 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.
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 $0.00064 $0.01057
Opus 5.5 $0.00026 $0.00423
Sonnet 5.5 $0.00013 $0.00211
Haiku 4.5 $0.00006 $0.00106

Measured 1mo ago against content hash 6267eceaec82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

.agents/skills/issue/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/issue — How Shift issues are written

An issue records an unmet product or engineering outcome. It explains the problem and the truth that must become observable without prescribing an unnecessary implementation.

Search before creation

Always search open and recently closed issues before creating one. Use several concise searches based on the user-visible behavior, domain terms, and likely title wording.

  • Reuse a matching open issue rather than creating a duplicate.
  • Reference a related issue when the scope overlaps but is not identical.
  • Inspect a matching closed issue before deciding whether the new report is a recurrence, a regression, or distinct work.
  • Never reopen or modify a closed issue without explicit user approval.

If an existing issue is adequate, return or update that issue instead of creating another.

Title

Use a concise outcome-oriented title that stands alone in issue lists. The title should:

  • describe the missing or incorrect behavior;
  • use direct, specific wording;
  • stay at or below 72 characters when practical;
  • omit trailing punctuation, emoji, agent labels, and implementation trivia.

Issues do not require a Conventional Commit prefix. Use fix:, feat:, or another type only when it is already part of an established issue series.

Body

Use the smallest body that makes the work testable:

## Problem

What is missing, broken, unsafe, or difficult, and why it matters.

## Expected outcome

What should be observably true when the issue is complete.

## Acceptance criteria

- [ ] concrete, verifiable result
- [ ] important safety or compatibility boundary

Add reproduction steps, evidence, constraints, or out-of-scope notes only when they materially clarify the issue. Do not copy an implementation plan into the issue unless the implementation boundary itself is a requirement.

Acceptance criteria must describe behavior or durable repository outcomes. Do not use vague criteria such as “works correctly,” “tests pass,” or “code is clean.”

Read the full file on GitHub · 98 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. 1mo ago First seen · 98 lines · 64 tokens per session scan A 6267eceaec82

Subscribe to this mod's changes

issue is a skill published in the GitHub repository shift-editor/shift (379 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,057 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-01.

Related

Other skills, from other repositories

gh-assign-issues

Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.

Hmbown/CodeWhale · 24 tokens

github

GitHub CLI (gh) for repository management, issues, pull requests, releases, workflows, search, gists, and API access. Use when the user asks about any GitHub operation — creating repos, forking, cloning, PR workflows, issue triage, CI/CD runs, code search, release management, or direct API calls. Keywords: github, gh…

bug-ops/zeph · 104 tokens

claim-issue

Atomically claim an issue for a developer (human or agent) via the cross-developer lock ref, so two devs never pick up the same task. Syncs with origin first, refuses if already claimed or already done on main, and pushes the claim immediately without touching main or triggering CI.

loopdive/js2 · 64 tokens

tuturuuu-agent-coordination

Coordinate Tuturuuu multi-agent programs, exact-head evidence, shared-worktree ownership, and handoffs.

tutur3u/platform · 28 tokens

pi-review-gated-delivery

Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.

spences10/my-pi · 40 tokens

tech-lead-loop

The tech lead's standing loop for keeping development unblocked across a sprint. Defines phase-by-phase protocol enforcement, merge-queue monitoring, and escalation triggers. Invoke at session start, again after every significant state change, and whenever devs look idle.

loopdive/js2 · 55 tokens