Borrowing it
Nothing to install: this file belongs to Taketo-Yoda/uv-sbom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Taketo-Yoda/uv-sbom/develop/.claude/skills/issue/SKILL.mdgit clone --depth 1 https://github.com/Taketo-Yoda/uv-sbomWrote 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/taketo-yoda/uv-sbom/issue)<a href="https://agentmods.dev/skills/taketo-yoda/uv-sbom/issue"><img src="https://agentmods.dev/badge/skills/taketo-yoda/uv-sbom/issue/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/taketo-yoda/uv-sbom/issue"><img src="https://agentmods.dev/badge/skills/taketo-yoda/uv-sbom/issue.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 | $0.00012 | $0.01036 |
| Opus 5.5 | $0.00005 | $0.00414 |
| Sonnet 5.5 | $0.00002 | $0.00207 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
issue 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 13d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/issue - Issue Creation Skill
Create GitHub Issues with consistent formatting and sufficient technical detail for autonomous implementation.
Language Requirement
IMPORTANT: All GitHub Issues MUST be written in English.
- Issue title: English
- Issue body: English
- Labels: English
- Comments: English
Steps
1. Read Issue Guidelines (MANDATORY)
Before drafting any Issue content, read:
.claude/issue-guidelines.md— full Issue creation guidelines, templates, and quality checklist
This file contains the authoritative structure, Pre-Submission Verification checklist, and examples of good/bad Issues.
2. Gather Information
After reading the guidelines, gather the following information from the user:
- Type: Feature, Bug, Documentation, Refactor, or other
- Summary: Brief description of the task
- Context: Why is this needed?
- Technical Details: Implementation hints if available (file paths, precedent Issues/PRs, invariants) — these go in the collapsed AI section
- Types affected: New or changed types, if any — these become the
## Design SketchMermaid diagram. If no types change, the Design Sketch section is omitted.
3. Draft Issue from Template
Use the template under ## Issue Structure Template in .claude/issue-guidelines.md
for Feature Requests. Use the template under ### Bug Report Template in
.claude/issue-guidelines.md for Bug Reports.
Follow the formatting rules under ## Issue Structure Template in
.claude/issue-guidelines.md — in particular, leave a blank line after <summary>
and before </details>.
Do not include implementation code in either section — see "No Implementation Code
in Issue Bodies" in .claude/issue-guidelines.md for the four allowed exceptions.
3.5. Convention Ownership Check (conditional)
Trigger: the draft's ## Files to Update/Create lists any path under .claude/.
Run the Convention Ownership Check in .claude/conventions/README.md against the
draft, and revise the draft until it passes. Then present the check's result lines
together with the draft, and wait for the user's confirmation before Step 5. When
another gate invokes /issue non-interactively (/code-review Step 3.5,
/implement Step 3.6), skip the wait and include the result lines in Step 6's
output instead.
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.
- 13d ago Changed 72409b09bad6
- 15d ago Changed · +1 lines 8733860754bc
- 19d ago Changed · +14 lines 8afbf7323399
- 22d ago Changed · -99 lines 756c3963554d
- 1mo ago Changed · +59 lines 593a70766792
- 1mo ago Changed 43543905a51b
- 1mo ago First seen · 148 lines · 12 tokens per session scan A 2b9e28110a55
issue is a skill published in the GitHub repository Taketo-Yoda/uv-sbom (6 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,036 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
select-build-target
Pull the next source contract to build from the pending backlog, respecting outside-in dependency order.
uv-docs
Astral uv 0.11.x — fast Python package and project manager in Rust. Projects, scripts, tools, Python versions, pip interface.
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
intake
Inspect configured Sources and propose evidence-backed Backlog work.
refresh
Refresh Product status from current work and source evidence.