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.
git clone --depth 1 https://github.com/Sagargupta16/claude-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/commands/sagargupta16/claude-skills/prep-pr)<a href="https://agentmods.dev/commands/sagargupta16/claude-skills/prep-pr"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-skills/prep-pr/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/commands/sagargupta16/claude-skills/prep-pr"><img src="https://agentmods.dev/badge/commands/sagargupta16/claude-skills/prep-pr.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 | $0.00013 | $0.00694 |
| Opus 5 | $0.00006 | $0.00347 |
| Sonnet 5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
prep-pr 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live state
- Branch: !
git rev-parse --abbrev-ref HEAD - Remote parent: !
gh repo view --json parent -q '.parent | "\(.owner.login)/\(.name)"' 2>/dev/null || echo "not a fork" - CONTRIBUTING: !
cat CONTRIBUTING.md 2>/dev/null | head -100 || cat .github/CONTRIBUTING.md 2>/dev/null | head -100 || echo "no CONTRIBUTING.md" - PR template: !
cat .github/PULL_REQUEST_TEMPLATE.md 2>/dev/null || cat .github/pull_request_template.md 2>/dev/null || echo "no PR template" - Diff stat: !
git diff $(git merge-base HEAD upstream/main 2>/dev/null || git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main)...HEAD --stat - Recent merged PRs (for style match): !
gh pr list --state merged --limit 3 --json title,body -q '.[] | "\(.title)\n\(.body | .[0:300])\n---"' 2>/dev/null || echo "gh unavailable"
Task
Prepare a PR for upstream review. Do not create it automatically.
- Read CONTRIBUTING.md above. Note CLA/DCO requirements, commit style, testing requirements, AI-disclosure rules.
- Match recent merged PRs. Tone, title format, body shape, body length.
- Quality-bar check (7+/10). Is this a real bug fix or meaningful feature? Skip self-promo awesome-list adds, trivial typos, docstring-only changes unless they fix a real issue.
- Scope discipline. Review diff stat above -- flag any files outside the issue's scope as drive-by changes to strip.
- Tests. Do tests exist for the change? Do they match upstream's test patterns (framework, fixtures, markers)?
- Rebase check. Is the branch up to date with
upstream/main? - Fill the PR template verbatim (if one exists above). Include AI-disclosure checkboxes when the repo asks for them.
- Project-specific conventions. If the upstream is Apache Airflow: use
[component] Descriptiontitle format, verify template-rendering tests usecreate_task_instance_of_operator.
Output
Upstream: <owner/repo>
Quality bar: <pass/fail + reason>
Scope: <narrow/wide + any drive-by files>
Tests: <match/mismatch + what>
Rebase: <up-to-date/behind-by-N>
PR template: <filled/missing/N-A>
Ready: <yes/no>
Blockers: <list or "none">
---
PROPOSED TITLE: <title>
PROPOSED BODY:
<filled template or shape>
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.
- 2d ago Changed 9c53d21040f7
- 9d ago First seen · 53 lines · 13 tokens per session scan A 35bda7a9dff0
prep-pr is a command published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 694 once invoked, about $0.0001 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 commands, from other repositories
commit
Create a git commit with intelligent message drafting (-f for fast, -v for verbose).
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
clean-gone
Clean up local branches that have been deleted from the remote repository.
commit-push-pr
Complete workflow — commit, push, and create a pull request in one step.
commit
Create a git commit with an automatically generated message based on staged and unstaged changes.
adk-ts-changelog
Generate changelog entries and community release notes for ADK-TS from git history and changesets.