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/yegor256/courier/submit-a-pull-requestnpx skills add yegor256/courier --skill submit-a-pull-requestgit clone --depth 1 https://github.com/yegor256/courierWrote 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/yegor256/courier/submit-a-pull-request)<a href="https://agentmods.dev/skills/yegor256/courier/submit-a-pull-request"><img src="https://agentmods.dev/badge/skills/yegor256/courier/submit-a-pull-request.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 | $0.00030 | $0.00489 |
| Opus 5 | $0.00015 | $0.00244 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
submit-a-pull-request 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Target
Target GitHub repository user named, or origin otherwise.
Use repository's actual default branch as base.
Resolve base branch at runtime, never hard-coding main.
Preconditions
Refuse on default branch or with dirty working tree. Refuse when no commits sit ahead of default branch. Refuse when open pull request already targets same branch. Confirm branch is up to date with remote default.
Boundaries
Submit commits untouched. Skip editing, amending, rebasing, squashing, building, testing, and linting.
Branch
Push branch before opening pull request.
Title
Use imperative-mood title, not Fixes or Update.
Derive title and body, never from branch name.
Body
Write body as few short paragraphs. Cover what changes, why, and any follow-up. Quote snippet of most important change, no longer than ten lines. Trust code to convey change better than prose.
Format
Shape pull request as imperative title plus short prose body. Shape comment as one or two sentences.
Voice
Write like human.
Vary rhythm, never sliding into AI cadence.
Open with substance, never with boilerplate or buzzword strings.
End body on last sentence.
Skip Generated with footers, Co-Authored-By trailers, and robot emoji.
Closing
Use closing keyword only when user or commit already cites issue.
Owner
Read owner from repository slug. For organization, use top recent committer as owner. Stop when owner stays unknown. Ask user to resolve it.
Comment
Skip comment when owner is authenticated account. Post one follow-up comment to owner otherwise. Mention owner in that comment. Offer to clarify in that comment. Keep comment to one or two sentences. Ping one account. Let owner set their own timing.
Example
Branch 42-retry adds retry logic and user says "open PR".
Push branch to origin.
Title pull request Add retry to courier client.
Write few short paragraphs covering change and motivation.
Quote most important change, under ten lines.
Ping owner once in follow-up comment.
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 First seen · 88 lines · 30 tokens per session scan A e6fe0f6a4851
submit-a-pull-request is a skill published in the GitHub repository yegor256/courier (3 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 489 once invoked, about $0.0002 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
code-review-checklist
Guide an AI agent through a structured code review — correctness, security, performance, readability, and test coverage — producing a summary with actionable, prioritized feedback. Triggers on pull-request review, diff review, or "review this code" requests.
github-mcp
Tools for interacting with the GitHub API, enabling file operations, repository management, search functionality, and more.
reissverschluss-merge
Reißverschluss-Verfahren (englisch: zipper merge) für sehr konfliktreiche Merges: Wenn zwei divergente Branches oder ein PR und sein Zielbranch BEIDE wertvolle, unvereinbar erscheinende Änderungen tragen, wird nicht pauschal eine Seite gewählt, sondern Abschnitt für Abschnitt verglichen, per Entscheidungstabelle…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…