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 skills add ymd38/dev-skills --skill yds-gh-issue-draftergit clone --depth 1 https://github.com/ymd38/dev-skillsWrote 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/ymd38/dev-skills/yds-gh-issue-drafter)<a href="https://agentmods.dev/skills/ymd38/dev-skills/yds-gh-issue-drafter"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-gh-issue-drafter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ymd38/dev-skills/yds-gh-issue-drafter"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-gh-issue-drafter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00227 | $0.01943 |
| Opus 5 | $0.00113 | $0.00971 |
| Sonnet 5 | $0.00045 | $0.00389 |
| Haiku 4.5 | $0.00023 | $0.00194 |
Grade A, and why
yds-gh-issue-drafter 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 10d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issue Drafter
Overview
The quality of everything downstream — the plan, the reviews, the implementation, the CI verification — is capped by the quality of the Issue that starts it. A rough, one-line Issue forces every later step to guess at the author's intent.
This skill takes the user's rough intent (the What) and, without slowing them down,
proposes the three things a hand-written Issue almost always omits: a machine-checkable
Done definition, an explicit Out of scope, and optional Design constraints.
The user approves or edits the proposal, then the skill creates a structured GitHub
Issue tagged with a marker that yds-gh-issue-planner recognizes.
Scope boundary: this skill only drafts and files the Issue. It does not investigate
code, propose a response plan, or implement anything. Hand off to yds-gh-issue-planner
once the Issue exists.
When NOT to expand
If the user's input already contains a clear Done definition and scope (e.g. they pasted
a fully-formed Issue, or a yds-report-to-issues output), do not re-interrogate them — just
confirm and file. The goal is to fill gaps, not to add ceremony to Issues that are
already well-formed.
Workflow
Step 1: Capture the rough intent
Take the user's input as the raw What. Do not ask them to rewrite it or expand it themselves — capturing intent cheaply is the whole point. If the input is a single line, that is fine.
If repository context is unclear, establish it:
gh repo view --json nameWithOwner
Step 2: Classify
Infer the Issue type to guide the Done definition and label. Keep it lightweight — one signal is enough.
| Signal in the intent | Type | Label | Done tends to look like |
|---|---|---|---|
| broken, error, crash, regression | Bug fix | bug |
a failing case now passes / reproduces no longer |
| add, support, new, want | Feature | feature |
new behavior is exercised by a test |
| clean up, restructure, extract, rename | Refactor | refactor |
behavior unchanged, tests still green |
| doc, readme, explain | Docs | docs |
the doc reflects current code |
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.
- 10d ago First seen · 179 lines · 227 tokens per session scan A cbe6ea584b60
yds-gh-issue-drafter is a skill published in the GitHub repository ymd38/dev-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 227 tokens to every session and 1,943 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
project-launch-checklist
Audits a project for hiring visibility before going public. Verifies README clarity for impatient hiring managers, checks evaluation setup, tests, CI/CD, config file, and deployment link. Generates a pre-launch audit report with gaps and priorities. Use when you're ready to make a project visible to hiring managers or…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.