BC-Bench is a benchmark for measuring coding agents on real-world Microsoft Business Central development tasks written in AL. It helps compare models and agent configurations using reproducible evaluation data.
Borrowing it
Nothing to install: this file belongs to microsoft/BC-Bench. 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/microsoft/BC-Bench/main/.github/skills/create-release/SKILL.mdgit clone --depth 1 https://github.com/microsoft/BC-BenchWrote 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/microsoft/bc-bench/create-release)<a href="https://agentmods.dev/skills/microsoft/bc-bench/create-release"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/create-release/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/microsoft/bc-bench/create-release"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/create-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00683 |
| Opus 5.5 | $0.00022 | $0.00273 |
| Sonnet 5.5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
create-release 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 1mo 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Release
Prepare release notes for maintainer review. Do not change versions, commit, tag, push, or create a GitHub release unless explicitly asked.
Workflow
- Establish the range: Read the version from
pyproject.tomland usev<version>as the target tag. If that tag exists, use it as the target ref and select the preceding semantic-version tag. Otherwise, useHEADas the target ref and select the latest reachable semantic-version tag. Ignore non-version tags such as evaluation-run tags. Exclude uncommitted changes and stop if the range is empty, ambiguous, or not fully available locally. - Study the format: Fetch and read the bodies of the three most recently published releases from
microsoft/BC-Bench. Match their concise paragraph style, spacing, and# Versionssection; do not use GitHub's automatically generated notes as the draft. - Screen merged PRs: Treat each commit in the complete
<previous-tag>..<target-ref>range as a merged PR. Review its title, changed files, and PR description, inspecting the diff only as needed to determine whether it may affect evaluation results. Classify every PR as included or omitted, but do not produce a PR-by-PR summary. - Select release-note content: Include only changes that may affect evaluation results or their comparability, such as dataset and gold-answer changes, evaluation logic, prompts, models, agent harnesses, tools, result schemas, and execution behavior. Combine related PRs into outcome-focused paragraphs. Omit formatting, linting, tests, documentation, refactoring, dependency maintenance, and CI housekeeping unless they change benchmark behavior or reproducibility. Call out compatibility boundaries explicitly.
- Collect shipped versions: Read the target ref, not the uncommitted worktree, and locate the exact pins for
@github/copilot,@anthropic-ai/claude-code, andMicrosoft.Dynamics.BusinessCentral.Development.Tools. Confirm duplicate pins agree. Never copy versions from an older release or infer them from commit messages. - Validate the draft: Ensure every claim is supported by an included PR, every PR in the range was classified, omitted PRs have no plausible evaluation impact, the target version is correct, and the three shipped versions are exact. Stop and report conflicting pins, missing history, or uncertain evaluation impact instead of guessing.
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.
- 1mo ago First seen · 35 lines · 56 tokens per session scan A dd83645dbb45
create-release is a skill published in the GitHub repository microsoft/BC-Bench (58 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 683 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.