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-report-to-issuesgit 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-report-to-issues)<a href="https://agentmods.dev/skills/ymd38/dev-skills/yds-report-to-issues"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-report-to-issues/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-report-to-issues"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-report-to-issues.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 | $0.00112 | $0.01541 |
| Opus 5 | $0.00056 | $0.00771 |
| Sonnet 5 | $0.00022 | $0.00308 |
| Haiku 4.5 | $0.00011 | $0.00154 |
Grade A, and why
yds-report-to-issues 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 9d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
Phase 1: Locate Report
- If the user specifies a file path, use it directly.
- Otherwise, list available reports:
docs/evaluation/— yds-software-evaluation reportsdocs/security-audit/— yds-vulnerability-scan reports- If multiple exist, ask the user to select one.
- Detect report type by content:
- Contains
## Improvement Roadmap→ evaluation report - Contains
## Remediation Priority→ security-audit report
- Contains
Phase 2: Extract Tasks
Evaluation report — extract rows from ## Improvement Roadmap tables (P0–P3):
Each row yields:
priority: P0 / P1 / P2 / P3title: Problem column (first sentence or file:line prefix)problem: full Problem cellsolution: Solution cellexpected_outcome: Expected Outcome cell
Security-audit report — extract from ## Remediation Priority table AND individual ## Findings sections:
Each row yields:
priority: P0 / P1 from Priority columntitle: Finding columnaction: Action columnbody: full finding detail from the matching### V-XXsection (Vulnerable Code, Attack Path, Risk Assessment, Recommended Fix)
Phase 3: Present Tasks for Selection
Display all extracted tasks before creating any issue:
Extracted tasks from <report file>:
1. [P0] <title> (<file:line if present>)
2. [P1] <title>
3. [P1] <title>
...
Which tasks would you like to register as GitHub Issues?
Enter numbers (e.g. 1 3 5), a range (e.g. 1-3), "all", or "none":
Wait for the user's response before proceeding.
Phase 4: Duplicate Detection
Before creating issues, check for existing issues that may overlap with the selected tasks.
4.1 Fetch existing open issues:
gh issue list --state open --json number,title,labels --limit 200
4.2 For each selected task, check for duplicates:
Compare the task title/problem against existing issue titles using keyword overlap. Flag a potential duplicate when:
- 3+ significant keywords match between the task and an existing issue title/body
- The same
file:linelocation is referenced - The same label combination exists (e.g., both
P0+security-audit)
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.
- 9d ago First seen · 207 lines · 112 tokens per session scan A b98955fd9144
yds-report-to-issues is a skill published in the GitHub repository ymd38/dev-skills (4 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,541 once invoked, about $0.0006 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
autonomous-pr
Otonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla. Budget ve zaman limiti ile kontrol altinda tutulan tam otonom PR pipeline'i.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
issues-workflow
Plan and track work using a GitHub Issues-first workflow with sub-issue hierarchies, issue-branch-PR lifecycle, and auto-close on merge.
issue-create
Create well-formatted GitHub issues with intelligent AI-powered label suggestions and content type detection. Use whenever the user wants to.
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.