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/pekral/cursor-rules/create-issues-from-textnpx skills add pekral/cursor-rules --skill create-issues-from-textgit clone --depth 1 https://github.com/pekral/cursor-rulesWhat 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 | $0.00015 | $0.00663 |
| Opus 5 | $0.00008 | $0.00331 |
| Sonnet 5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
create-issues-from-text 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issues from Text
Purpose
Split a complex assignment into multiple clear, structured issues.
Constraints
- Preserve original assignment (store in parent or first issue)
- Do not implement code
- Assign all issues to current user
- Use CLI tools
Execution
1. Analyze Assignment
- Understand scope and dependencies
- Identify logical implementation steps
2. Propose Breakdown
- List steps with short descriptions
- Proceed directly to step 3; do not gate on a confirmation round when the breakdown is unambiguous
3. Create Issues
- One issue per step
- Ensure each is independently deliverable
- Assign the most relevant existing label to each issue (per
@rules/compound-engineering/general.mdcAssign the most relevant existing label when creating a tracker issue)
4. Output
- Return list of created issues with URLs
Issue Structure
Use the template defined in templates/issue-structure.md.
EPIC parent & sub-issues
Use this when the assignment is a cross-cutting mix of requirements spanning multiple parts of the application (e.g. backend + frontend + mobile, or schema + API + UI). Instead of a flat list of peer issues, build a parent → children tree so the whole effort is trackable from one place.
- Pick (or create) the parent. When the assignment already has a tracker item, that item becomes the EPIC parent. When the assignment is a described task with no tracker item, create the parent issue first, carrying the full original assignment in its body.
- Label the parent
EPIC. Apply theEPIClabel to the parent. Create the label once if the repository does not have it yet (gh label create EPIC --description "Tracks a cross-cutting effort split into sub-issues" --color 5319e7), then ignore the "already exists" outcome on subsequent runs. - Create one sub-issue per application area. Each sub-issue is an independently deliverable assignment (same
templates/issue-structure.mdstructure) scoped to a single area; do not bundle two areas into one sub-issue. - Link every sub-issue back to the parent (both directions).
- In each sub-issue body, reference the parent with
Part of #<parent>so the relationship is visible from the child. - In the parent body, keep a checkable task list of the children —
- [ ] #<child>per sub-issue — under a## Sub-issuesheading, so the parent shows the full breakdown and progress.
- In each sub-issue body, reference the parent with
- Order. Fill each sub-issue's
## Dependenciesso a resolving run can pick a dependency-aware order — dependencies before dependents. - Output. Return the
EPIC-labelled parent URL plus the list of linked sub-issue URLs and the planned resolve order.
What ships with it
1 file 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.
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 · 62 lines · 15 tokens per session scan A bbbc35b78ddb
create-issues-from-text is a skill published in the GitHub repository pekral/cursor-rules (6 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 663 once invoked, about $0.0001 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
migrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
ponytail-help
Quick reference for ponytail's modes, skills, and commands. One-shot display.
laravel-best-practices
Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization…
parse-table
Parse table definition to extract module name, model name, table name, and field definitions. First step of CRUD generation.
owl-admin-ops-commands
Use this skill for Owl Admin installation, publishing assets, upgrades, diagnostics, database inspection, menu maintenance, user creation, password reset, route generation, IDE helper, admin:publish, admin:install, admin:update, admin:doctor, admin:db, admin:menu, admin:create-user, or deployment troubleshooting.
octane-development
Use this skill when working with Laravel Octane, a long-running PHP worker server (Swoole, FrankenPHP, RoadRunner) where the application boots once and serves many requests instead of rebooting for each request like PHP-FPM. Trigger when installing Octane or starting its server; configuring or detecting the active…