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/prs-awaiting-maintainernpx skills add dyoshikawa/rulesync --skill prs-awaiting-maintainergit 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/prs-awaiting-maintainer)<a href="https://agentmods.dev/skills/dyoshikawa/rulesync/prs-awaiting-maintainer"><img src="https://agentmods.dev/badge/skills/dyoshikawa/rulesync/prs-awaiting-maintainer.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 | $0.00056 | $0.00857 |
| Opus 5 | $0.00028 | $0.00428 |
| Sonnet 5 | $0.00011 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
prs-awaiting-maintainer 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 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.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List PRs Awaiting Maintainer Action
Identify open pull requests where the ball is in the maintainer's court — the PR is ready and the next action belongs to a maintainer (review, re-review, or merge), not the author.
Signals That the Ball Is on the Maintainer's Side
- CI is fully green: every check is passing, with none failing or pending.
- The PR is not a draft.
- And at least one of:
- The PR was newly opened and has not been reviewed yet (awaiting first review).
- The author pushed new commits after a
CHANGES_REQUESTEDreview (re-review needed). - The author has replied to or resolved the review comments and is now waiting on the maintainer.
- A maintainer review was requested and has not yet been provided.
- The most recent meaningful activity is from the author (or CI) — not an unanswered maintainer question.
Exclude a PR when the next action clearly belongs to the author (see the complementary prs-awaiting-author skill): CI failing, unaddressed review comments, changes requested without follow-up commits, or an open maintainer question awaiting the author's reply.
Step 1: List Open Non-Draft PRs
gh pr list --state open --limit 100 --json number,title,author,isDraft,createdAt,updatedAt,url,reviewDecision,reviewRequests
Skip any PR where isDraft is true.
Step 2: Gather Per-PR Signals
For each candidate PR, gather details (run in parallel across PRs where practical):
- CI status:
gh pr checks <number>— treat as green only if every check is passing and none are pending or failing. - Reviews and decision:
gh pr view <number> --json reviewDecision,reviews,latestReviews,reviewRequests. - Discussion and who spoke last:
gh pr view <number> --comments, and if neededgh api repos/{owner}/{repo}/pulls/<number>/commentsfor inline review threads. - Commit timeline vs. last review time: to determine whether the author pushed commits after a
CHANGES_REQUESTEDreview.
The maintainers for this repository are dyoshikawa and cm-dyoshikawa; use this login list as the primary way to tell the maintainer side from the author side. Note that gh pr view --json does not expose author_association — that field is only available per comment or review through gh api repos/{owner}/{repo}/pulls/<number>/comments and the reviews endpoint, where an author_association of OWNER, MEMBER, or COLLABORATOR indicates the maintainer 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 · 61 lines · 56 tokens per session scan A 257483276c3a
prs-awaiting-maintainer is a skill published in the GitHub repository dyoshikawa/rulesync (1,385 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 857 once invoked, about $0.0003 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.
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…