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/shopwarelabs/ai-coding-tools/pr-description-writingnpx skills add shopwareLabs/ai-coding-tools --skill pr-description-writinggit clone --depth 1 https://github.com/shopwareLabs/ai-coding-toolsWrote 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/shopwarelabs/ai-coding-tools/pr-description-writing)<a href="https://agentmods.dev/skills/shopwarelabs/ai-coding-tools/pr-description-writing"><img src="https://agentmods.dev/badge/skills/shopwarelabs/ai-coding-tools/pr-description-writing.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 5.1 | $0.00144 | $0.01750 |
| Opus 5 | $0.00072 | $0.00875 |
| Sonnet 5 | $0.00029 | $0.00350 |
| Haiku 4.5 | $0.00014 | $0.00175 |
Grade A, and why
pr-description-writing 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 5d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Description Drafting
Draft a PR title (conventional commit format) and description (Shopware's 5-section template) by analyzing the full branch scope, leveraging session context, and asking targeted questions for missing context.
Output scope: Presents formatted title + description text. Does not create or update PRs on GitHub. Does not write to any files.
Phase 1 — Assess Branch State
Determine what we're working with — branch, PR status, and diff.
- Load
references/branch-and-pr-detection.mdand execute Steps 1-4. Route aspr-description-writing. - Get the diff:
- If a PR exists: read its diff and changed files from GitHub (a GitHub MCP server, the
ghCLI, or the API — whatever the session has) - If no PR: run
git diff trunk...HEAD --statandgit log trunk..HEAD --oneline
- If a PR exists: read its diff and changed files from GitHub (a GitHub MCP server, the
- Present a brief assessment to the user: branch name, PR status (exists / doesn't exist / has existing description), change magnitude (files touched, lines changed, areas affected)
Phase 2 — Analyze Changes
Understand the full story of the branch — not just individual file changes.
- Synthesize the full branch scope from the diff, commits, and file changes. Understand the totality: features, fixes, cleanups, refactors — everything that happened on this branch.
- Determine scope: map file paths to Shopware areas (Core, Storefront, Administration, App System, etc.). This informs the conventional commit scope for the title.
- Identify the narrative candidates. A branch often contains multiple threads — a feature plus cleanup plus a fix discovered along the way. Present these to the user:
"This branch contains: (a) a new endpoint for X, (b) a fix for null handling in Y, (c) cleanup of unused imports. What's the primary story?"
- The user confirms or reframes the story. This drives the title's type/scope and which aspects get depth vs. a brief mention. If secondary threads remain (cleanup, test improvements, incidental fixes), offer them as an "Additional Changes" section: "The test cleanup / refactor / fix isn't part of the main story. Want it mentioned in an Additional Changes section at the end?" Only offer when the secondary work has educational value (practices not widely known in the project) or touches files a reviewer might otherwise question.
- Assess description depth based on the confirmed story:
- Bug fix → root cause analysis in Why, reproduction steps important
- New feature → usage context in What, scope boundaries valuable
- Breaking change → migration guidance needed
- Performance → quantified improvement expected
- Leverage session context: if the user has been debugging, implementing, or discussing in the current session, use that knowledge. Don't re-ask what's already known.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 101 lines · 144 tokens per session scan A 9c0e7690a4f7
pr-description-writing is a skill published in the GitHub repository shopwareLabs/ai-coding-tools (43 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 1,750 once invoked, about $0.0007 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
implement
Execute approved plans, fix bugs, and make code changes inline with incremental validation. TDD by default, build+test after each logical block, commit at green checkpoints, and divergence detection that routes back to planning instead of pushing through a broken approach. Use when: 'implement this', 'execute the…
batch-simplify
Batch-run simplification across changed files, or across an entire repository, grouped by ecosystem and dependency order. Use when: 'batch simplify', 'simplify recent changes', 'simplify everything', 'forgot to run simplify', 'catch up on simplify', 'simplify my branch changes', 'simplify the whole repo', 'simplify…
audit-permission-state
Report the Claude Code permission state actually in effect. Discovers every settings scope (managed policy, user-global, project, local, and the pre-v2.1.211 start-directory copy), merges them into the effective allow/ask/deny set with each rule's source and precedence mechanic named, and classifies which allow rules…
audit-native-overlap
Map native Claude Code surfaces (built-in CLI commands, bundled skills, plugin-backed built-ins, session-provided skills) against the current repo's plugin skills and agents, so a custom component never silently duplicates what Claude Code itself now ships. Bare invocation is a READ-ONLY report: overlap candidates…
research-deep
Dispatch deep external research to the heaviest isolated execution tier available, a workflow engine, an isolated subagent, or inline as last resort, keeping the main conversation clean while the full research discipline runs. Itself runs in main context, the only place both the Workflow tool (absent from every…
audit-encapsulation
Audit and remediate skill-encapsulation violations. External citations reaching into private surfaces inside .claude/skills/ / or plugins/ /skills/ / (marketplace monorepos) beyond the slash invocation. Use when: 'audit encapsulation', 'find skill leaks', 'skill boundary violation', 'who is reaching into ', 'check…