triage-issue

triage-issue is a skill for Claude Code, Codex from encoreshao/encore-skills. It costs 59 tokens per session (1,395 once invoked), scanned A, original, MIT.

A GitLab issue-comment workflow for deciding which comments need a reply and drafting responses based on the actual codebase.

In plain words
What is it for?
Use it to review an issue's discussion, identify comments directed at you, investigate the relevant code, and prepare grounded replies.
Why use it?
It prevents missed questions and avoids replies based only on guesses. Every proposed reply is shown for confirmation before it is posted.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to review an issue's discussion, identify comments directed at you, investigate the relevant code, and prepare grounded replies.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/encoreshao/encore-skills/triage-issue"><img src="https://agentmods.dev/badge/skills/encoreshao/encore-skills/triage-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,395 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 $0.00059 $0.01395
Opus 5 $0.00030 $0.00698
Sonnet 5 $0.00012 $0.00279
Haiku 4.5 $0.00006 $0.00139

Measured 11d ago against content hash 5d04e79c9400, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

triage-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 11d 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/triage-issue/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Issue

Reads an issue and its comment thread, figures out which comments genuinely need a reply from you, grounds the reply in the actual codebase (not guesswork), drafts it in your own voice, and shows it to you — every time, no exceptions — before anything gets posted.

Input

  • Issue number (#42) with project alias or path, or a GitLab URL
  • A local clone of the relevant repo, if you want the reply grounded in current code (optional — skip Step 3 if there's no codebase)
GITLAB="$HOME/.claude/skills/gitlab-config/scripts/gitlab_api.py"
python $GITLAB whoami                            # confirm your username once per session
python $GITLAB sync-project <project>             # once per project — builds the team/user directory
python $GITLAB sync-issue <project> <number>      # issue + full comment thread, merged into the cache

See gitlab-config skill for first-time setup and the local-memory cache it maintains.

Steps

1. Fetch the issue and comments

Use sync-issue, not get-issue — same API call, but it merges onto whatever's already cached for this issue instead of discarding it, so any comment you've already handled (see Step 4) stays marked. It returns the issue plus every note in notes[], oldest-last. Each note has author, body, system (true = GitLab-generated, e.g. "assigned to @x" — never needs a reply), and created_at.

Resolve @mentions and author names against the cached team directory (gitlab_cache.py get-users <instance>) instead of guessing from the raw GitLab username — it's already built from sync-project and every issue you've synced.

2. Decide which comments need your reply

Walk the notes in chronological order (reverse the array first — GitLab returns newest-first). Skip system notes, anything you authored, and any note id already listed in the cached _notes.replied_note_ids (see Step 4 — you've handled it in a prior run). For everything else, a comment needs your reply if:

  • It @mentions your username directly, or
  • You're the assignee, it asks a direct question or requests an action, and no later comment from you addresses it

Read the full file on GitHub · 88 lines

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. 11d ago First seen · 88 lines · 59 tokens per session scan A 5d04e79c9400

Subscribe to this mod's changes

triage-issue is a skill published in the GitHub repository encoreshao/encore-skills (2 stars, last pushed 22d ago), licensed MIT. It adds 59 tokens to every session and 1,395 once invoked, about $0.0003 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.