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-summarize-pullgit 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-summarize-pull)<a href="https://agentmods.dev/skills/amonstack/gitea_mcp/gitea-summarize-pull"><img src="https://agentmods.dev/badge/skills/amonstack/gitea_mcp/gitea-summarize-pull/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.
<a href="https://agentmods.dev/skills/amonstack/gitea_mcp/gitea-summarize-pull"><img src="https://agentmods.dev/badge/skills/amonstack/gitea_mcp/gitea-summarize-pull.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00139 | $0.00588 |
| Opus 5.5 | $0.00056 | $0.00235 |
| Sonnet 5.5 | $0.00028 | $0.00118 |
| Haiku 4.5 | $0.00014 | $0.00059 |
Grade A, and why
gitea-summarize-pull 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 1mo 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-summarize-pull
When to use
Trigger when the user asks to summarize a PR for review — 中文请求如「总结一下这个 PR」「这个 PR 改了什么、能不能合」也 MUST 走本 skill。
Read a pull request and its discussion, then synthesize. Tools: get_pull_request, list_pull_commits, list_pull_files, list_comments.
Prerequisites
- Resolve
owner+repo: pass explicitly, elseGITEA_DEFAULT_OWNER/GITEA_DEFAULT_REPO, elseresolve_repo(gitea-resolve-repo).
Flow
get_pull_request({ index })—index= PRnumber(URL #N → N), never the internalid. Read title, body,base/head,mergeable,merged,draft, labels, milestone.list_pull_commits({ index })— the commit history (page iflength === limit).list_pull_files({ index })— the diff scope: filenames, statuses, additions/deletions (page iflength === limit).list_comments({ index })— the review discussion. PR #N == Issue #N — the comment endpoints are shared.
list_comments — TRUNCATION TRAP
- This tool passes NO page/limit and returns at most the server's default page size. For long review threads the list is SILENTLY TRUNCATED. If the
commentscount (fromget_pull_request) exceeds the number returned, warn that part of the thread is missing and do NOT claim a complete summary.
Synthesis
- Report: the PR state (open/closed/merged/draft), WHAT it changes (from commits + files), the mergeability/conflict status, then the thread's consensus / decisions / open questions. Attribute by author. Flag unresolved review feedback or blocking questions explicitly — do not paper over disagreement. End with one recommended NEXT ACTION (merge / request changes / close).
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.
- 1mo ago Changed · +4 lines · +41 tokens per session e07648316798
- 1mo ago First seen · 24 lines · 98 tokens per session scan A 67d6f84bbb28
gitea-summarize-pull is a skill published in the GitHub repository amonstack/gitea_mcp (1 stars, last pushed 21d ago), licensed MIT. It adds 139 tokens to every session and 588 once invoked, about $0.0006 per session on Opus 5.5. 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-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…