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/create-issue-with-websearchnpx skills add dyoshikawa/rulesync --skill create-issue-with-websearchgit 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/create-issue-with-websearch)<a href="https://agentmods.dev/skills/dyoshikawa/rulesync/create-issue-with-websearch"><img src="https://agentmods.dev/badge/skills/dyoshikawa/rulesync/create-issue-with-websearch.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 | $0.01529 |
| Opus 5 | $0.00015 | $0.00764 |
| Sonnet 5 | $0.00006 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
create-issue-with-websearch 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
topic = the user's request
Use this skill when the user only has a rough, fuzzy idea and needs heavy web research to clarify the target specification before creating an issue. If the user already has a concrete, well-scoped task in mind, use the create-issue skill instead.
Step 1: Gather the Initial Idea
Receive the topic from topic or the user's description.
If the input is very sparse, ask the user just enough to anchor the research:
- What is the rough area or goal? (e.g., a tool to support, a feature to add, a behavior to change)
- Why do they want it — what problem or limitation triggered the idea?
- Any hard constraints known up front (must/must-not, scope boundaries)?
Do not push for full specification details at this stage. The point of this skill is to resolve the unknowns through research, not to force the user to resolve them manually.
Step 2: Research the Topic on the Web
Investigate the topic thoroughly using WebSearch and WebFetch. The goal is to raise the resolution of the specification until concrete, defensible design decisions become possible.
Look for, as applicable to the topic:
- Official documentation of any tool, standard, protocol, or API involved — prefer primary sources over blog posts.
- File formats, configuration schemas, naming conventions, and default locations used by the target tool(s).
- Feature support matrices: project vs. global scope, supported file types, known limitations.
- Recent changes, deprecations, or pre-release behavior that might affect the design.
- Prior art: how similar tools or competing implementations solve the same problem.
- Existing discussions (GitHub issues, release notes, RFCs) that reveal open questions or community expectations.
Guidelines while researching:
- Run multiple searches in parallel when the angles are independent.
- Cross-check claims against at least one primary source before relying on them.
- Capture exact URLs, version numbers, and quoted snippets as you go — they will be cited in the issue.
- If a source disagrees with another, note the disagreement explicitly rather than silently picking one side.
- Stop expanding research once the open questions needed to draft the issue are answered; avoid rabbit holes unrelated to the decision.
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 · 147 lines · 30 tokens per session scan A 4ac718f59d0b
create-issue-with-websearch is a skill published in the GitHub repository dyoshikawa/rulesync (1,379 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,529 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
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…
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…
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…