write-issue

write-issue is a skill for Claude Code, Codex from encoreshao/encore-skills. It costs 29 tokens per session (504 once invoked), scanned A, original, MIT.

A writing tool that turns a rough bug report or feature idea into a structured GitLab issue. GitLab is a service for hosting code and tracking development work.

In plain words
What is it for?
Use it to draft issue titles, descriptions, labels, testable requirements, and out-of-scope notes.
Why use it?
It replaces vague requests with a clear problem, likely cause, expected result, and acceptance criteria that can be tested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to draft issue titles, descriptions, labels, testable requirements, and out-of-scope notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/encoreshao/encore-skills/write-issue
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.

Any agent
npx skills add encoreshao/encore-skills --skill write-issue
Clone the repo
git clone --depth 1 https://github.com/encoreshao/encore-skills

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 write-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/encoreshao/encore-skills/write-issue.svg)](https://agentmods.dev/skills/encoreshao/encore-skills/write-issue)
Your own site
<a href="https://agentmods.dev/skills/encoreshao/encore-skills/write-issue"><img src="https://agentmods.dev/badge/skills/encoreshao/encore-skills/write-issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 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 $0.00029 $0.00504
Opus 5 $0.00015 $0.00252
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00050

Measured 7d ago against content hash 378c62ff4f8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

write-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 7d 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.

skills/write-issue/SKILL.md · 72 lines

What it actually says

Write Issue

Use when you have a rough idea, bug report, or feature request that needs to become a trackable GitLab issue.

Steps

1. Nail the problem first

Before writing anything, ask:

  • What is actually broken or missing? (the symptom)
  • Why does it happen? (the root cause — for bugs)
  • Who is affected and how often?
  • What does "fixed" look like?

Don't start drafting until you can answer these. A vague issue creates vague work.

2. Draft the issue

Title: Short, imperative, problem-focused.

  • Bug: Users cannot log in when email contains uppercase letters
  • Feature: Add CSV export to the reports page
  • No [Type] prefix — use labels for that.

Description:

## Problem
What is broken or missing? What is the root cause (for bugs)?
Be specific — include error messages, affected users, frequency.

## Expected behavior
What should happen instead?

## Acceptance Criteria
- [ ] <specific, testable outcome — not "it works">
- [ ] <regression test covers this case>
- [ ] <no related behavior is broken>

## Out of scope
What this issue does NOT cover. Prevents scope creep.

Labels: bug / feature / improvement + area (backend, frontend, design)

3. Sanity check before submitting

Ask yourself:

  • Could an engineer start working on this without asking you any questions?
  • Are the acceptance criteria specific enough to verify with a test?
  • Is the root cause identified (for bugs) or is it still a guess?

If not — improve the issue before creating it.

4. Create

# With glab
glab issue create --title "TITLE" --description "DESCRIPTION" --label "bug,backend"

# Without glab: copy the text and paste into GitLab
Files

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.

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. 7d ago First seen · 72 lines · 29 tokens per session scan A 378c62ff4f8b

Subscribe to this mod's changes

write-issue is a skill published in the GitHub repository encoreshao/encore-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 29 tokens to every session and 504 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.