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 amonstack/gitea_mcp --skill gitea-resolve-repogit 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-resolve-repo)<a href="https://agentmods.dev/skills/amonstack/gitea_mcp/gitea-resolve-repo"><img src="https://agentmods.dev/badge/skills/amonstack/gitea_mcp/gitea-resolve-repo.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 | $0.00125 | $0.00585 |
| Opus 5 | $0.00063 | $0.00293 |
| Sonnet 5 | $0.00025 | $0.00117 |
| Haiku 4.5 | $0.00013 | $0.00059 |
Grade A, and why
gitea-resolve-repo 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 4d 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.
What it actually says
gitea-resolve-repo
When to use
Trigger when the target repository is unknown or the user asks which repos the token can access — 中文请求如「该操作哪个仓库」「列出我能访问的仓库」「这个项目的 owner/repo 是什么」也 MUST 走本 skill。
Discover the target repository and instance. Tools: resolve_repo, list_my_repos.
resolve_repo
- Reads
.git/configof the git repo atpath(default: current directory) and parses EVERY remote from SSH ([email protected]:owner/repo.git) or HTTPS (https://gitea.example/owner/repo.git) URLs. - Selects the remote to target in this priority:
upstream→origin→ any other. SSH remotes resolve tobaseUrl = https://<host>(the API is assumed HTTPS). - Returns
{ baseUrl, owner, repo, remote, remote_url, remotes: { <name>: {baseUrl, owner, repo, url} } }. ReadbaseUrlto know which instance a token must be valid for; readremotesto see upstream vs origin when they differ. - Throws
No parseable git remotes foundif the cwd has no git remote or none parse. Do NOT guess owner/repo from context — call this, or ask the user.
list_my_repos
- Lists repositories the token can access. GLOBAL. Returns large objects — paginate (
limit≤ 100) and read only the fields you need (name, full_name, owner.login). If this returns 401/403 there is no usable token — switch to the gitea-configure skill.
Resolution order (every repo-scoped tool)
explicit owner/repo args → GITEA_DEFAULT_OWNER/GITEA_DEFAULT_REPO (or git-discovered
defaults) → resolve_repo. If none resolve, the tool throws owner and repo are required.
Wrong values 404 or silently target the wrong repo — never guess.
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.
- 4d ago Changed · +4 lines · +50 tokens per session 3506d93fd97a
- 7d ago First seen · 30 lines · 75 tokens per session scan A 9da39762da9f
gitea-resolve-repo is a skill published in the GitHub repository amonstack/gitea_mcp (1 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 585 once invoked, about $0.0006 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…