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 instructions/kbennett2000/concord-mcp/claude-mdgit clone --depth 1 https://github.com/kbennett2000/concord-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/instructions/kbennett2000/concord-mcp/claude-md)<a href="https://agentmods.dev/instructions/kbennett2000/concord-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kbennett2000/concord-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01283 | $0.01283 |
| Opus 5 | $0.00642 | $0.00642 |
| Sonnet 5 | $0.00257 | $0.00257 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
concord-mcp CLAUDE.md 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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — concord-mcp
What this is
A read-only MCP (Model Context Protocol) server exposing Concord's /v1
Scripture API as tools for LLM clients (Claude Desktop, Claude Code, MCP
Inspector, and any MCP-speaking client). It is a sibling of songbird: a
consumer of the /v1 contract, never a fork of the engine.
It is also the destination codebase for the planned concord-tutorial-ai
course. A tutorial graduate must be able to read this repo top to bottom in
one sitting. Smallness and clarity beat cleverness everywhere. If a change
makes the repo harder for that reader, it needs a very good reason.
How we work
- Spec first.
docs/v1/SPEC.mdis the source of truth. Read it and this file before any work. Enter Plan Mode before implementing any slice, and present the plan for approval before writing code. - One PR per slice. Smallest reviewable, load-bearing unit. The slice plan
is SPEC §11. Branches:
feat/<short-name>offmain. Conventional commits (feat(tools): …,fix(http): …,docs: …). - Bobby (kbennett2000) merges every PR. Never self-merge. Never push to
mainafter the bootstrap commit. Never force-push, anywhere, ever. - Draft PRs at human gates. Any PR whose checklist includes a step only Bobby can perform (live verification against his LAN Concord, client testing in Claude Desktop) opens as a GitHub draft until that step is checked off.
- Read the source, don't guess. Response shapes come from Concord's
docs/API.mdand itsbible_apischema code — read them, never invent fields. If the spec and observed reality disagree, stop and surface it; the spec is amended in the same PR, never silently drifted from. - ADRs. Any architectural decision (new dependency, new transport,
contract change, tool-surface change) gets
docs/adr/NNNN-*.mdin the same PR. ADRs 0001–0004 are binding. - Stop and report. Every slice ends with: verification output, test counts, the PR URL, and any deviations with rationale.
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.
- 5d ago First seen · 99 lines · 1,283 tokens per session scan A 41f9c645dacf
concord-mcp CLAUDE.md is an instructions file published in the GitHub repository kbennett2000/concord-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 1,283 tokens to every session, about $0.0064 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 instructions, from other repositories
swiss-statistics-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-statistics-mcp, covering claude.md, teil 1 — portfolio-konventionen, vor der arbeit, tests and wenn etwas rot ist.
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.
leanforge-mcp CLAUDE.md
Claude Code instructions for sandraschi/leanforge-mcp, covering claude.md -- leanforge-mcp, what this repo does, key concepts, when working on agent.py and when working on leanclient.py.
aviasales-mcp AGENTS.md
AGENTS.md instructions for stufently/aviasales-mcp, covering agents.md, layout, conventions, build and test and gotchas.
math-mcp-learning-server AGENTS.md
AGENTS.md instructions for clouatre-labs/math-mcp-learning-server, covering math mcp learning server - python mcp server [production], stack, structure, commands and project-specific patterns.
mgi-link AGENTS.md
AGENTS.md instructions for berntpopp/mgi-link, covering agents.md — engineering conventions for mgi-link, golden rules, architecture invariants (do not break), fleet deploy contract and data plane.