A command that creates one Linear issue for each work slice already listed in a project's scope.json file. It can also save the issue IDs back into that file or write the issues to a Markdown document when Linear is unavailable.

Use it to turn planned feature slices into Linear tasks, such as for a login page or reporting dashboard. It reads the project's plan and requirements to build the issue details and acceptance criteria.

It lets you recreate or publish work issues without repeating the entire planning process. This is useful when the plan already exists but the issue list needs to be created again.

to-issues — Command by saitarrun

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 commands/saitarrun/devforge-ai/to-issues

Clone the repo

git clone --depth 1 https://github.com/saitarrun/Devforge-ai

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,053 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.

Model	Per session	Once invoked
Fable 5	$0.00040	$0.01053
Opus 5	$0.00020	$0.00526
Sonnet 5	$0.00008	$0.00211
Haiku 4.5	$0.00004	$0.00105

Measured 2d ago against content hash de9cfa790b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

to-issues 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 2d 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.

commands/to-issues.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/to-issues — Create issues from scope.json slices

Reads ./projects/<feature-name>/scope.json (and optionally docs/01-prd.md) and creates one Linear issue per slice. Updates scope.json with linear_id on each slice after creation.

Usage

/to-issues "login-page"
/to-issues "reporting-dashboard"

The <feature-name> must match the directory under ./projects/.

EXECUTION

STEP 1: Read artifacts

Read ./projects/<feature-name>/scope.json
Read ./projects/<feature-name>/docs/01-prd.md if it exists (used for issue descriptions)
Read ./projects/<feature-name>/grill-summary.md if it exists (used for acceptance criteria)

If scope.json is missing, halt:

❌ scope.json not found at ./projects/<feature-name>/scope.json

Run /sdlc-plan or /to-prd first to generate scope.json.

If slices already have linear_id set, warn the user:

⚠️  Some slices already have linear_id set:
  slice-0 → SAI-XX
  slice-1 → SAI-XX

Proceeding will create NEW issues for all slices and overwrite linear_id.
Reply "yes" to continue or "no" to abort.

STEP 2: Create issues

If Linear MCP is available:

For each slice in scope.json:

Create a Linear issue with:

Title: slice name
Labels: prefactor (if type = prefactor) or feature (if type = feature)

Description (Markdown):

## Slice: [slice id] — [slice name]

**Type**: [prefactor | feature]
**Layers**: [comma-separated layers]

## Context

[Summary from grill-summary.md or 01-prd.md scoped to this slice — what the user should be able to do when this slice is complete]

## Acceptance Criteria

- [ ] [layer: schema] Database schema migrated and seeded
- [ ] [layer: api] Endpoint(s) implemented and returning correct responses
- [ ] [layer: ui] UI component(s) implemented matching ux-design.md specs
- [ ] [layer: tests] Unit + integration tests written with >80% coverage
- [ ] typecheck passes
- [ ] slice tests pass

(Only include rows for layers listed in this slice's layers array)

Read the full file on GitHub · 145 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.

2d ago First seen · 145 lines · 40 tokens per session scan A de9cfa790b38

Subscribe to this mod's changes

to-issues is a command published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,053 once invoked, about $0.0002 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.

Project management agentic-ai claude-code-plugin codex-plugin software-architecture software-development software-engineering

to-issues

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/to-issues — Create issues from scope.json slices

Usage

EXECUTION

STEP 1: Read artifacts

STEP 2: Create issues

What this file has done since we first saw it

Other commands, from other repositories

sdlc

sdlc-retrospective

team

codev

tasks-to-ado

sdlc-dev