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/synthaicode/xrefkit.mcp/agents-mdgit clone --depth 1 https://github.com/synthaicode/XRefkit.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 | $0.00244 | $0.00244 |
| Opus 5 | $0.00122 | $0.00122 |
| Sonnet 5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
XRefkit.MCP 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 2d 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
Personal Codex instruction
This user works with XRefKit-style repository governance.
At session start, follow the repository-defined loading process and treat loaded AGENTS.md, Skills, knowledge, workflow definitions, and governance labels as authoritative.
Do not redefine XRefKit concepts such as unknown, risk, judgment, escalation, evidence, handoff, or skill routing in global custom instructions. Use the repository definitions.
Global instructions should only control:
- concise communication
- progress visibility
- explicit summary of changes
- explicit list of unverified items
- respect for repository-defined stop-and-escalate rules
If a required rule is missing, do not invent a project rule. Mark it as missing and suggest whether it belongs in AGENTS.md, a Skill, knowledge, or workflow definition.
--- project-doc ---
AGENTS Startup (XRefKit MCP)
As your first action, read the MCP startup contract below:
README.md#ai-client-instruction-templateREADME.md#required-client-startup-flow
When working against an XRefKit repository through this MCP server, call get_startup_context first and resolve XID-linked documents with get_document_by_xid.
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.
- 2d ago First seen · 28 lines · 244 tokens per session scan A b5e04e93ecae
XRefkit.MCP AGENTS.md is an instructions file published in the GitHub repository synthaicode/XRefkit.MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 244 tokens to every session, about $0.0012 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
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
rosetta AGENTS.md
Instructions for tikoci/rosetta, covering codex instructions for rosetta, first reads, development defaults and mcp and client config.
pharo-smalltalk-interop-mcp-server CLAUDE.md
Instructions for mumez/pharo-smalltalk-interop-mcp-server, covering claude.md, project overview, development setup, environment variables and common commands.