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 skills add grandcamel/GitLab-Assistant-Skills --skill gitlab-discussiongit clone --depth 1 https://github.com/grandcamel/GitLab-Assistant-SkillsWrote 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.
[](https://agentmods.dev/skills/grandcamel/gitlab-assistant-skills/gitlab-discussion)<a href="https://agentmods.dev/skills/grandcamel/gitlab-assistant-skills/gitlab-discussion"><img src="https://agentmods.dev/badge/skills/grandcamel/gitlab-assistant-skills/gitlab-discussion.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00055 | $0.02622 |
| Opus 5 | $0.00028 | $0.01311 |
| Sonnet 5 | $0.00011 | $0.00524 |
| Haiku 4.5 | $0.00006 | $0.00262 |
Grade A, and why
gitlab-discussion 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 6d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discussion Skill
Threaded discussion management for GitLab using glab api raw endpoint calls.
Quick Reference
| Operation | Command Pattern | Risk |
|---|---|---|
| List MR discussions | glab api projects/:id/merge_requests/:iid/discussions |
- |
| List issue discussions | glab api projects/:id/issues/:iid/discussions |
- |
| Get discussion | glab api projects/:id/merge_requests/:iid/discussions/:id |
- |
| Create discussion | glab api projects/:id/merge_requests/:iid/discussions -X POST -f ... |
⚠️ |
| Reply to discussion | glab api projects/:id/.../discussions/:id/notes -X POST -f ... |
⚠️ |
| Resolve discussion | glab api projects/:id/.../discussions/:id -X PUT -f resolved=true |
⚠️ |
| Delete note | glab api projects/:id/.../discussions/:id/notes/:nid -X DELETE |
⚠️⚠️ |
Risk Legend: - Safe | ⚠️ Caution | ⚠️⚠️ Warning | ⚠️⚠️⚠️ Danger
When to Use This Skill
ALWAYS use when:
- User mentions "discussion", "thread", "conversation"
- User wants to add code review comments
- User mentions "resolve", "unresolve" discussions
- User wants to reply to existing comments/threads
- User wants line-specific comments on MRs
NEVER use when:
- User wants simple notes/comments (use
glab mr noteorglab issue note) - User wants to review MR changes (use gitlab-mr)
- User wants to search comments (use gitlab-search with
notesscope)
API Prerequisites
Required Token Scopes: api
Permissions:
- Read discussions: Reporter+ (for private repos)
- Create discussions: Reporter+
- Resolve discussions: Developer+ (or MR author)
Available Commands
List MR Discussions
# List all discussions on MR
glab api projects/123/merge_requests/1/discussions --method GET
# With pagination
glab api projects/123/merge_requests/1/discussions --paginate
# Using project path
glab api "projects/$(echo 'mygroup/myproject' | jq -Rr @uri)/merge_requests/1/discussions"
List Issue Discussions
# List all discussions on issue
glab api projects/123/issues/42/discussions --method GET
# With pagination
glab api projects/123/issues/42/discussions --paginate
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.
- 6d ago First seen · 303 lines · 55 tokens per session scan A 9fd2f111b4a6
gitlab-discussion is a skill published in the GitHub repository grandcamel/GitLab-Assistant-Skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 55 tokens to every session and 2,622 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.
Other skills, from other repositories
review-health
Audit any repository's structural health and file the findings as proposed epics and one-PR issues.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
techdebt
Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.