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/microsoft/hve-core/gitlabnpx skills add microsoft/hve-core --skill gitlabgit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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 | $0.00014 | $0.02476 |
| Opus 5 | $0.00007 | $0.01238 |
| Sonnet 5 | $0.00003 | $0.00495 |
| Haiku 4.5 | $0.00001 | $0.00248 |
Grade A, and why
gitlab 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 yesterday.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab Skill
Overview
Use this skill to inspect and update GitLab merge requests, notes, pipelines, and job logs against GitLab.com or self-managed GitLab instances.
This skill is the repository-local Python workflow for GitLab tasks. It is not the official GitLab MCP server integration surface.
This first hve-core implementation is Python-only. Run the CLI through
python scripts/gitlab.py and prefer --fields for read operations to keep
output concise.
Prerequisites
The skill requires Python 3.11 or later.
Set these environment variables before running any command:
| Variable | Required | Example | Purpose |
|---|---|---|---|
GITLAB_URL |
Yes | https://gitlab.com |
GitLab instance URL |
GITLAB_AUTH_MODE |
Optional | oauth |
oauth or explicit legacy-token compatibility mode |
GITLAB_OAUTH_CLIENT_ID |
OAuth | Application ID | Non-confidential OAuth application ID; no client secret |
GITLAB_TOKEN |
Legacy mode | glpat-... |
PAT accepted only with GITLAB_AUTH_MODE=legacy-token |
GITLAB_PROFILE |
No | default |
Named OAuth profile |
GITLAB_TOKEN_STORE |
No | path | OAuth store override; parent must be owner-only on POSIX |
GITLAB_ALLOW_INSECURE |
No | 1 |
Permit explicit loopback HTTP development endpoints only |
XDG_DATA_HOME |
No | path | POSIX data root used for the default OAuth store |
LOCALAPPDATA |
No | path | Reserved Windows data root; OAuth persistence currently fails closed on Windows |
GITLAB_PROJECT |
No | group/project |
Project path or numeric project ID |
What ships with it
57 files 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.
- pyproject.toml 681 B
- scripts/_gitlab_credentials.py 15 KB runs code
- scripts/_gitlab_oauth.py 24 KB runs code
- scripts/gitlab.py 52 KB runs code
- SECURITY.md 33 KB
- tests/conftest.py 3.8 KB runs code
- tests/corpus/0_empty 1 B
- tests/corpus/0_large 2.0 KB
- tests/corpus/0_no_suffix 5 B
- tests/corpus/0_remote_path 18 B
- tests/corpus/0_unicode 11 B
- tests/corpus/0_with_suffix 9 B
- tests/corpus/0814fd5a169c01a1448b1817d8ac617d6f277db8 6 B
- tests/corpus/1_empty 1 B
- tests/corpus/1_float 5 B
- tests/corpus/1_large 15 B
- tests/corpus/1_negative 3 B
- tests/corpus/1_numeric_id 6 B
- tests/corpus/1_valid_id 6 B
- tests/corpus/2_deeply_nested 604 B
- tests/corpus/2_empty 1 B
- tests/corpus/2_field_path 12 B
- tests/corpus/2_nested_json 26 B
- tests/corpus/2_unicode 29 B
- tests/corpus/3_empty 1 B
- tests/corpus/3_json_payload 15 B
- tests/corpus/3_large 2.0 KB
- tests/corpus/3_malformed 10 B
- tests/corpus/3_trailing 10 B
- tests/corpus/3_valid_json 35 B
- tests/corpus/4_empty 1 B
- tests/corpus/4_float 5 B
- tests/corpus/4_large 15 B
- tests/corpus/4_negative 3 B
- tests/corpus/4_positive_int 3 B
- tests/corpus/4_unicode 10 B
- tests/corpus/4_zero 2 B
- tests/corpus/5_empty 1 B
- tests/corpus/5_field_flag 18 B
- tests/corpus/5_large 899 B
- tests/corpus/5_mr_list 8 B
- tests/corpus/5_multi_field 25 B
- tests/corpus/5_single_field 12 B
- tests/corpus/5_unicode 25 B
- tests/corpus/ee123d57ee4d24cece23066fb721013d717824f2 37 B
- tests/corpus/README.md 1.5 KB
- tests/fuzz_harness.py 7.6 KB runs code
- tests/test_constants.py 1.2 KB runs code
- tests/test_gitlab_audit.py 7.7 KB runs code
- tests/test_gitlab_commands.py 10 KB runs code
- tests/test_gitlab_coverage.py 4.2 KB runs code
- tests/test_gitlab_credentials.py 12 KB runs code
- tests/test_gitlab_helpers.py 18 KB runs code
- tests/test_gitlab_main.py 11 KB runs code
- tests/test_gitlab_oauth.py 18 KB runs code
- tests/test_gitlab_transport.py 30 KB runs code
- uv.lock 57 KB
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.
- yesterday First seen · 200 lines · 14 tokens per session scan A 1050858be902
gitlab is a skill published in the GitHub repository microsoft/hve-core (1,405 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 2,476 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…