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/amonstack/gitea_mcp/gitea-configurenpx skills add amonstack/gitea_mcp --skill gitea-configuregit clone --depth 1 https://github.com/amonstack/gitea_mcpWrote 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/amonstack/gitea_mcp/gitea-configure)<a href="https://agentmods.dev/skills/amonstack/gitea_mcp/gitea-configure"><img src="https://agentmods.dev/badge/skills/amonstack/gitea_mcp/gitea-configure.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 | $0.00152 | $0.01478 |
| Opus 5 | $0.00076 | $0.00739 |
| Sonnet 5 | $0.00030 | $0.00296 |
| Haiku 4.5 | $0.00015 | $0.00148 |
Grade C, and why
gitea-configure scanned grade C with 1 finding 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 today.
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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
store file (`~/.git-credentials`). If `gitea_status` reports How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gitea-configure
When to use
Trigger when the user asks to configure / set up / fix the Gitea connection, instance URL, or token, or any tool call fails with 401/403 — 中文请求如「配置 Gitea 连接」「令牌怎么设」「为什么报 401 没权限」也 MUST 走本 skill。
Diagnose and fix the Gitea connection. The server auto-discovers its config from the project's git remotes; this skill is the fallback when that fails or the token is wrong.
How gitea-mcp discovers config (no env vars required)
On start, the server reads <cwd>/.git/config and resolves in this order:
- baseUrl —
GITEA_BASE_URLenv var; else theGITEA_REPO_URLrepo URL's host; else derived from the selected remote's host. SSH remotes (git@host:owner/repo) resolve tohttps://host. - owner / repo —
GITEA_DEFAULT_OWNER/GITEA_DEFAULT_REPOenv vars; else theGITEA_REPO_URLrepo URL's path; else from the selected remote's URL. - Remote selection —
upstreamremote first, falling back toorigin, then any other remote. Both are surfaced inresolve_repooutput (with embedded userinfo stripped from every echoed URL).
If the working directory has NO git remote and neither GITEA_BASE_URL nor
GITEA_REPO_URL is set, the server
starts in an unconfigured state — tools/list is available, but business tools
return NotConfiguredError. Use the configure_gitea tool to set the connection at
runtime (session-scoped, never persisted), or guide the user to restart from a cloned
repo / with env vars set.
Token discovery chain (tried in order)
GITEA_REPO_URL— a self-contained credentialed clone URL (https://<user>:<token>@<host>[:<port>]/<owner>/<repo>.git) whose userinfo becomes the top-priority candidate when the URL points at the instance host..git/config— a[gitea "<baseUrl>"]section (read viagit config get --url=<baseUrl> gitea.token), e.g.
A bare[gitea "https://gitea.example.com"] token = <your-token>[gitea]section withtoken = ...is a host-wide fallback.GITEA_TOKENenv var.- The credential git itself would use for the instance host, retrieved via
git credential fill— this honors every configured credential helper, including OS keychains (wincred/osxkeychain/libsecret) and the store file (~/.git-credentials). Ifgitea_statusreportsgitAvailable: false, git could not be used at all — only the env sources (GITEA_REPO_URL/GITEA_TOKEN) remain; guide the user to install git (≥ 2.46) or setGITEA_TOKEN/GITEA_REPO_URL. - If none of the above yield a token, the server starts WITHOUT a token (anonymous). Public repos may be read; writes and private repos return 401 — that is the signal to help the user add a token via one of the sources above.
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.
- today Changed · +14 lines · +58 tokens per session 2489344fa627
- 4d ago First seen · 76 lines · 94 tokens per session scan C 55dff8b259c4
gitea-configure is a skill published in the GitHub repository amonstack/gitea_mcp (1 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 1,478 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…