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/keithdev21/business-central-mcp/releasenpx skills add keithdev21/Business-Central-Mcp --skill releasegit clone --depth 1 https://github.com/keithdev21/Business-Central-McpWhat 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 | $0.00131 | $0.02439 |
| Opus 5 | $0.00066 | $0.01220 |
| Sonnet 5 | $0.00026 | $0.00488 |
| Haiku 4.5 | $0.00013 | $0.00244 |
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 yesterday.
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 This is a copy
100% identical to bc-mcp-release — 0 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 — 254 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 --noEmit, 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.
- yesterday First seen · 254 lines · 131 tokens per session scan C 834f16110737
bc-mcp-release is a skill published in the GitHub repository keithdev21/Business-Central-Mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 131 tokens to every session and 2,439 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to bc-mcp-release, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.