Borrowing it
Nothing to install: this file belongs to SShadowS/business-central-mcp. 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/SShadowS/business-central-mcp/master/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/SShadowS/business-central-mcpWrote 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/sshadows/business-central-mcp/release)<a href="https://agentmods.dev/skills/sshadows/business-central-mcp/release"><img src="https://agentmods.dev/badge/skills/sshadows/business-central-mcp/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/sshadows/business-central-mcp/release"><img src="https://agentmods.dev/badge/skills/sshadows/business-central-mcp/release.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 | $0.00152 | $0.02591 |
| Opus 5.5 | $0.00061 | $0.01036 |
| Sonnet 5.5 | $0.00030 | $0.00518 |
| Haiku 4.5 | $0.00015 | $0.00259 |
Grade C, and why
bc-mcp-release scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
cd .. && rm -rf bc-mcp-smoke Copies of this mod
4 near-identical copies found in the catalogue:
- bc-mcp-release — 100% identical, 61 lines differ
- bc-mcp-release — 100% identical, 61 lines differ
- bc-mcp-release — 100% identical, 61 lines differ
- bc-mcp-release — 100% identical, 61 lines differ
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bc-mcp release runbook
Release business-central-mcp to npm. The package is configured for manual
publish via prepublishOnly (typecheck + build); the rest is gated by you
to keep destructive operations safe.
This is a runbook, not an automated tool. Walk the user through each step, pausing on anything destructive (version bump, publish, tag push) for explicit confirmation. Releases are irreversible — npm allows unpublish only within 72 hours of publish, and only if no other package depends on the exact version.
Preflight checklist
Run these before suggesting a version bump. If any fail, stop and surface the failure — don't paper over it.
cd U:/Git/bc-mcp # or wherever the repo lives
# Working tree clean?
git status --short # expect empty
git rev-parse --abbrev-ref HEAD # expect master
# Up-to-date with origin?
git fetch origin
git status -sb # expect "## master...origin/master" with no behind/ahead
# All tests pass?
npm run typecheck # tsc on src and on src+tests (tsconfig.test.json), expect exit 0
npm test # unit + protocol, expect green
npm run test:integration # against live BC, expect green (skip if no BC available, but flag the skip)
# CHANGELOG up-to-date?
grep -q "^## \[Unreleased\]" CHANGELOG.md && echo "OK: [Unreleased] section exists"
# Inspect the [Unreleased] section — it should describe what's about to ship.
If integration tests can't run (no live BC), explicitly tell the user
"integration tests skipped — running CI to compensate". CI will run unit +
protocol on Node 20/22/24 against the master branch via
.github/workflows/ci.yml.
Step 1: Pick the version
Read package.json to see the current version. Compare against published
versions on npm:
npm view business-central-mcp versions --json
Decide the bump per semver:
| Change kind | pre-1.0 (0.x.y) |
post-1.0 (x.y.z) |
|---|---|---|
| Bug fix only | 0.x.y patch |
x.y.z patch |
| New feature, backwards-compatible | 0.x.0 minor |
x.y.0 minor |
| Breaking change to public API | 0.x.0 minor (allowed pre-1.0) |
x.0.0 major |
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.
- 9d ago Changed · -3 lines · +21 tokens per session eba25aaa7000
- 14d ago Changed 3a06794ecd2f
- 1mo ago First seen · 254 lines · 131 tokens per session scan C 834f16110737
bc-mcp-release is a skill published in the GitHub repository SShadowS/business-central-mcp (46 stars, last pushed 6d ago), licensed MIT. It adds 152 tokens to every session and 2,591 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
maintaining-python-tests
Maintains existing pytest and Django test suites without weakening correctness. Use when asked to reduce Python test runtime or CI work, investigate slow pytest families, remove stale migration tests, consolidate repeated setup, improve Python test ownership, or measure whether a test optimization worked after merge.…
agent-starters
Verify every starter supported by the stable production NVIDIA Elements CLI from a fresh consumer environment, investigate failures, and prepare at most one focused repair pull request. Use for nightly or scheduled production starter verification and starter availability failures.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
merge-wave
Triage N open PRs with sharded test262 results, rank by net pass delta, merge winners, close catastrophes. Use when multiple PRs have completed CI and you want to land a batch.