agentmods.dev

rosetta issue-pr-linking.instructions.md

A rule for connecting GitHub issues with pull requests, which are proposed code changes. Completed issues must be closed from the pull request, while incomplete work must be split into follow-up issues.

In plain words
What is it for?
Use it when preparing pull request descriptions, handling partial implementations, or managing umbrella issues and their child tasks.
Why use it?
It keeps issue status accurate and prevents partially delivered work from being treated as finished.

Instructions file for GitHub Copilot

43 17d ago A scan 354 tokens original MIT
View the source file tikoci/rosetta
Install

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.

agentmods
npx agentmods add instructions/tikoci/rosetta/issue-pr-linking
Clone the repo
git clone --depth 1 https://github.com/tikoci/rosetta

Made for: GitHub Copilot.

Per session 354 This file is loaded in full into every session.
When invoked 354 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00354 $0.00354
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured 3d ago against content hash ad898ed652f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rosetta issue-pr-linking.instructions.md 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 3d 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.

.github/instructions/issue-pr-linking.instructions.md · 25 lines

What it actually says

Issue ↔ PR linking

Work is tracked in GitHub Issues; PRs are how issues close. Two rules, both mandatory:

  1. Link to close. A PR that implements an issue states Closes #N (or Fixes #N) in the PR body — not only in a comment or commit message — so the merge closes the issue automatically. One Closes #N line per issue the PR fully resolves. If a PR merely relates to an issue without finishing it, say Part of #N instead, which does not auto-close.

  2. Partial landings spawn follow-ups before merge. If the PR delivers only part of the issue, do not leave the issue half-open-half-done. Before merging: open a follow-up issue for each undone remainder (carrying over the relevant acceptance bullets and V-* validation rows), reference the follow-ups from the PR body, and then it is fine to Closes #N the original. An issue should always be either fully delivered or explicitly split — never silently narrowed by what the PR happened to include.

Umbrella issues (umbrella label) are never closed by a PR directly — they close manually when their child checklist is done. Check off the child in the umbrella body when the child closes.

Changes

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.

  1. 3d ago First seen · 25 lines · 354 tokens per session scan A ad898ed652f9

Subscribe to this mod's changes

rosetta issue-pr-linking.instructions.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 17d ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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.

Git and workflowProject managementaibunclaude-codecopilotmcpmcp-server
Related

Other instructions, from other repositories

bun-mcp copilot-instructions.md

Copilot instructions for TomasHubelbauer/bun-mcp, covering github copilot instructions for the bun-mcp repository and formatting.

TomasHubelbauer/bun-mcp · 253 tokens

memorix GEMINI.md

Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.

AVIDS2/memorix · 846 tokens

calc-mcp CLAUDE.md

Instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.

coo-quack/calc-mcp · 1,417 tokens

mcp-security-scanner CLAUDE.md

Instructions for badchars/mcp-security-scanner, covering mcp-security-scanner — mcp security scanner, architecture, key rules, tool categories (43 tools) and commands.

badchars/mcp-security-scanner · 442 tokens

relay AGENTS.md

Instructions for ImBIOS/relay, covering agents.md — relay, project overview, tech stack, architecture and support policy.

ImBIOS/relay · 1,340 tokens

copilot-mcp CLAUDE.md

Claude Code instructions for VikashLoomba/copilot-mcp, covering claude.md, project overview, development commands, root directory commands and install dependencies for both extension and web ui.

VikashLoomba/copilot-mcp · 1,291 tokens