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/davidmosiah/delx-mcp-server/agents-mdgit clone --depth 1 https://github.com/davidmosiah/delx-mcp-serverWrote 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/davidmosiah/delx-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/davidmosiah/delx-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmosiah/delx-mcp-server/agents-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 | $0.00293 | $0.00293 |
| Opus 5 | $0.00147 | $0.00147 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
delx-mcp-server AGENTS.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.
What it actually says
Agent Development Notes
Scope
This repo is the native stdio bridge for the hosted Delx Protocol MCP endpoint. It does not contain Delx backend logic, credentials, reward accounting, databases, or private infrastructure.
Commands
- Install:
npm ci - Health check:
npm run doctor - Tool list check:
npm run list-tools - Full gate:
npm test - Package preview:
npm pack --dry-run
Rules
- Keep the package a thin transport bridge from local stdio to the bounded Protocol endpoint
https://api.delx.ai/v1/mcp/protocol?src=npm-bridge. - Never commit credentials, local client config, private endpoint overrides, or generated MCP client files.
- Do not add backend-only Delx logic here. Hosted protocol behavior belongs behind the API.
- Keep install commands copyable for Claude Desktop, Cursor, Codex, Gemini, and other MCP clients.
- Mutating install helpers must preserve dry-run/JSON preview behavior.
Agent-readiness checklist
Before publishing a new version:
npm testnpm run doctor -- --jsonagainst the default endpoint when network is availablenpm pack --dry-runand confirm the package only includes bridge/runtime docs- Bump
package.jsonandserver.jsontogether - Re-check README install snippets for stale package names or endpoints
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 · 32 lines · 293 tokens per session scan A 5eabdda16458
delx-mcp-server AGENTS.md is an instructions file published in the GitHub repository davidmosiah/delx-mcp-server (0 stars, last pushed 7d ago), licensed MIT. It adds 293 tokens to every session, about $0.0015 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
MTA_Plugin CLAUDE.md
Claude Code instructions for GRU-953/MTA_Plugin, covering claude.md — memorised them all, resume protocol (every session), status, invariants (must never regress) and env notes.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
goodboy AGENTS.md
AGENTS.md instructions for akhayam99/goodboy, covering agents.md, where new code goes, naming, components and exports and store selectors and memoization.
goodboy CLAUDE.md
Claude Code instructions for akhayam99/goodboy, covering goodboy (claude-specific notes), stack quick-reference and claude-specific notes.
ls-mcp AGENTS.md
AGENTS.md instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.