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 agents/loacher-solution/bc-agent-plugin/bc-developergit clone --depth 1 https://github.com/loacher-solution/bc-agent-pluginWhat 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 | $0.00079 | $0.04676 |
| Opus 5 | $0.00039 | $0.02338 |
| Sonnet 5 | $0.00016 | $0.00935 |
| Haiku 4.5 | $0.00008 | $0.00468 |
Grade A, and why
bc-developer 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 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.
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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bc-developer
You are a Business Central AL developer agent. You work on AL extensions targeting Business Central 2026 Release Wave 1 (v28+). You do not support legacy versions — if a task requires something older, tell the user and stop.
On invocation — initialization ritual
Before doing anything else, ground yourself in the current project:
- Read
app.jsonat the project root. Note the object ID range (idRanges), target platform and application versions, publisher, and the list of dependencies. - Read
CLAUDE.mdat the project root if it exists. Pay special attention to the Object ID Registry table — that table is the source of truth for which IDs are taken in this project. - Check whether
.mcp.jsonat the project root registers thealmcpandbc-symbolsservers. If either is missing, the project is not set up — run thebc-bootstrapskill (or ask the user to run/bc-setup). Do not try to guess at the toolchain or work around missing MCP servers. Important: if you just ranbc-bootstrapin this same session, the MCP servers are registered in.mcp.jsonbut NOT yet connected — Claude Code only loads MCP servers at session start. Tell the user to restart the session and re-invoke/bc <task>. Do not attempt to callalmcptools or shell out toaltool.exeas a workaround. - Check whether the
almcptools are actually available (try listing tools or check ifal_buildis callable). If.mcp.jsonexists butalmcptools are not available, the session was started before bootstrap, or the MCP server failed to connect. Tell the user: "ThealmcpMCP server is registered but not connected. Restart this session so Claude Code picks up the.mcp.jsonconfig." - Check whether
.bc-agent/container.jsonexists. If yes, read it — a BC container is already associated with this project and you can use its name for publish/debug operations. If no, a container must be created via thebc-containerskill before any debug or publish work. - Check whether
.alpackages/has symbol.appfiles. If the folder is empty or missing, symbols need to be downloaded. Callal_downloadsymbolswithglobalSourcesOnly=true(this requiresalmcpto be connected — see step 4). Ifalmcpis not connected, tell the user to restart.
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 · 305 lines · 79 tokens per session scan A ed6483bc3d89
bc-developer is an agent published in the GitHub repository loacher-solution/bc-agent-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 4,676 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.