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/post-issue-commentnpx skills add dyoshikawa/rulesync --skill post-issue-commentgit clone --depth 1 https://github.com/dyoshikawa/rulesyncWhat 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 | $0.00031 | $0.00491 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
post-issue-comment 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 2d 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
arguments = the user's request
Parse arguments as:
target_issue: the issue number (or URL) to reply tointent: the gist of the reply the user wants to post (what to say, the stance to take, the points to cover)
If target_issue is not provided, ask the user which issue to comment on.
If intent is not provided, ask the user what the reply should convey.
Step 1: Gather Issue Context
Run the following in parallel:
- Get the issue description and metadata:
gh issue view <issue_number> - Get the issue comments:
gh issue view <issue_number> --comments
If the issue references related pull requests, commits, or files that are needed to craft an informed reply, gather that context as well.
Step 2: Draft the Reply
Based on the issue content and the user's intent, draft a reply comment.
- Ground the reply in the actual discussion — address the latest comment or the original issue as appropriate.
- Reflect the user's
intentfaithfully; do not add positions the user did not ask for. - If relevant context is missing or a decision cannot be made without more information, say so in the reply rather than guessing.
Step 3: Post the Comment
Post the drafted reply using:
gh issue comment <issue_number> --body "<reply body>"
Writing Style
Write in English only.
Style guidelines — write like a human teammate, not a bot:
- Use plain paragraphs. Avoid headings (
##), horizontal rules (---), and excessive bullet lists. - Keep it conversational and direct. Say what matters, skip the filler.
- Do not use phrases like "Great point!" or "Thanks for raising this!" unless you genuinely mean it and have nothing else to add.
- Be honest. If you disagree or see an issue, say so clearly but respectfully.
- Short is fine. A two-sentence comment is better than a five-paragraph essay with no substance.
Step 4: Report
Output the issue number and a brief summary of the comment that was posted.
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.
- 2d ago First seen · 60 lines · 31 tokens per session scan A 859020fd4c08
post-issue-comment is a skill published in the GitHub repository dyoshikawa/rulesync (1,373 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 491 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 2026-08-30.
Other skills, from other repositories
deep-clean
Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…
turborepo
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
skill-creator-anthropic
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
skill-creator-openai
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…