Rulesync is a command-line tool that generates configuration for different AI development tools from a shared set of rules. Developers use it to keep instructions, commands, MCP settings, ignore files, subagents, and skills consistent across coding agents. Catalogue skills support workflows built around Rulesync.
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/dyoshikawa/rulesync/draft-issue-to-external-repositorynpx skills add dyoshikawa/rulesync --skill draft-issue-to-external-repositorygit clone --depth 1 https://github.com/dyoshikawa/rulesyncWrote 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/dyoshikawa/rulesync/draft-issue-to-external-repository)<a href="https://agentmods.dev/skills/dyoshikawa/rulesync/draft-issue-to-external-repository"><img src="https://agentmods.dev/badge/skills/dyoshikawa/rulesync/draft-issue-to-external-repository.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 | $0.00079 | $0.01772 |
| Opus 5 | $0.00039 | $0.00886 |
| Sonnet 5 | $0.00016 | $0.00354 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
draft-issue-to-external-repository scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If the proposal includes popularity / adoption claims, verify the numbers before writing them down. For npm downloads: `curl -s "https://api.npmjs.org/downloads/point/<start>:<end>/<package>"`. For stars/forks: `gh rep How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arguments = the user's request
Parse arguments as:
target_repo: the target repository inowner/repoform (or a URL)intent: the rough idea the user wants to propose (may be vague — this skill is designed to sharpen it)
If target_repo is not provided, ask the user which repository to file against.
If intent is not provided, ask the user what they want to propose.
This skill is for proposing a change to a repository we do not own. When the target is a repo under the user's own owner, prefer create-issue or create-issue-with-websearch instead.
Step 1: Inspect the Target Repository
Before drafting anything, understand the target repo's conventions. Run in parallel:
gh repo view <owner/repo> --json description,url,defaultBranchRef,primaryLanguage,latestReleasegh issue list --repo <owner/repo> --limit 20 --state all --json number,title,labels,state— read recent titles to learn the house style (prefix tags like[FEATURE], casing, length).gh api repos/<owner/repo>/contents/.github/ISSUE_TEMPLATE— list templates. If a feature-request template exists, fetch it withgh apior a raw URL and note the required sections plus any auto-applied title prefix / labels.gh label list --repo <owner/repo>— note which labels exist (do not invent labels later).- Optionally fetch
CONTRIBUTING.md/CODE_OF_CONDUCT.mdif present to catch any issue-filing rules.
If no issue template exists, plan to use a light structure (Problem / Proposal / Alternatives / Additional context) that mirrors common feature-request templates.
Step 2: Research the Topic
Ground the proposal in primary sources before writing anything opinionated.
- Use
WebSearch/WebFetchfor official docs of the target project, release notes, and any pre-existing discussion (open/closed issues, PRs, RFCs). - Use the deepwiki MCP (
mcp__deepwiki__ask_question,mcp__deepwiki__read_wiki_contents) against the target repo for structural questions — it is often faster and more definitive than grepping manually. - For deep or multi-angle investigation, delegate to a subagent (
Agentwithsubagent_type: "general-purpose") with a self-contained prompt. Ask for a definitive answer, not a hedged summary. - Cross-check any claim the draft will rely on against at least one primary source. If two sources disagree, note the disagreement in the draft rather than silently picking a side.
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.
- 6d ago First seen · 122 lines · 79 tokens per session scan A 9e7d5c9eccbb
draft-issue-to-external-repository is a skill published in the GitHub repository dyoshikawa/rulesync (1,385 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,772 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…