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 sandbaseai/sandbase-skills --skill pr-draft-summarygit clone --depth 1 https://github.com/sandbaseai/sandbase-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/sandbaseai/sandbase-skills/pr-draft-summary)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/pr-draft-summary"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/pr-draft-summary/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/sandbaseai/sandbase-skills/pr-draft-summary"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/pr-draft-summary.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 | $0.00040 | $0.00599 |
| Opus 5.5 | $0.00016 | $0.00240 |
| Sonnet 5.5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
pr-draft-summary 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 28d 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.
This is a copy
73% identical to accessibility-review — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Draft Summary
Use this Skill to produce a bounded, verifiable PR Draft Summary outcome. Preserve the user's chosen stack, source material, and authorization boundaries.
Read the SandBase API map only when the task genuinely needs an external data source or generative model.
Workflow
- Inspect the available files, runtime, versions, inputs, and existing conventions before deciding what to change.
- Restate the requested outcome, constraints, acceptance checks, and any assumption that could change the result.
- Produce the smallest complete implementation, analysis, or artifact that satisfies those checks.
- Verify the real output with appropriate tests, previews, calculations, or source comparison; do not infer success from file creation alone.
- Return the deliverable, evidence of validation, material assumptions, and unresolved limitations.
Quality gates
- Inspect repository instructions, current versions, tests, and user changes before proposing an implementation.
- Make the smallest compatible change, preserve public contracts unless change is requested, and avoid new dependencies without a concrete benefit.
- Run focused tests plus the relevant build or static checks, then report observed results and any unverified paths.
- Do not stage, commit, push, open a pull request, tag, publish, or discard changes unless the user requested that exact action.
SandBase boundary
Keep the core PR Draft Summary work local. Use SandBase only for current external documentation, repository evidence, or explicitly requested model inference.
- Call
sandbase_discoverwith a short capability query. - Call
sandbase_inspectfor viable candidates and compare the live schema, coverage, limits, output, execution mode, and price. - Prefer a dedicated tool or API the user already has. Send only the minimum necessary data.
- Before any paid call, show the endpoint, important arguments, current unit price, call count, and total estimate or uncertainty, then obtain confirmation.
- Use
sandbase_accountbefore an approved multi-call batch and callsandbase_runonly with current schema-defined arguments. - Poll asynchronous work with
sandbase_run_getusing the same run ID; never resubmit merely because it is pending. - Use
sandbase_runsonly to recover status or reconcile observed cost.
What ships with it
1 file 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.
- 28d ago First seen · 44 lines · 40 tokens per session scan A 61cc4af0e056
pr-draft-summary is a skill published in the GitHub repository sandbaseai/sandbase-skills (202 stars, last pushed 29d ago), licensed Apache-2.0. It adds 40 tokens to every session and 599 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 73% identical to accessibility-review, differing in 18 lines, and is treated as a copy.
Other skills, from other repositories
github-publish-changes
Publish intentional local changes by confirming scope, creating a branch when needed, staging selected files, committing, pushing, and creating a Draft Pull Request through the connected GitHub service.
commit-message
Guidance for writing Git commit messages using Conventional Commits, a common format such as fix, feat, or docs followed by a short description. It focuses on explaining why a change was made.
github-pr-best-practices
Best practices for creating GitHub pull requests including conventional commits, PR formatting, and multi-language support (en/ja). Use when creating PRs, writing PR descriptions, or formatting commit messages.
git-workflow
Enhanced git operations using lazygit, gh (GitHub CLI), and delta. Triggers on: stage changes, create PR, review PR, check issues, git diff, commit interactively, GitHub operations, rebase, stash, bisect.
gh-publish
Publish task-scoped changes to GitHub through a branch/commit/push/PR flow, including fork-based external contributions. Use when the user wants changes pushed or a PR opened; draft PR is the default.
code-review-zh
A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.