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/nexenio/bifrost-plugin/agents-mdgit clone --depth 1 https://github.com/neXenio/bifrost-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 | $0.00947 | $0.00947 |
| Opus 5 | $0.00474 | $0.00474 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
bifrost-plugin 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bifrost-plugin — AGENTS.md
Skill Discovery — check before non-trivial work (MANDATORY)
The bifrost MCP gateway may expose a shared skill library and a set of MCP
servers (docs, search, issue tracker, memory, etc.) — whatever your gateway is
configured to route to.
BEFORE starting any non-trivial task — implementing a feature, writing a
migration, debugging, reviewing a PR, deploying, setting up infra, writing tests,
or drafting docs — you MUST call the gateway's skill-search tool, typically
mcp__bifrost__<skills-server>-skill_search (the skill server is named
skills by default; set BIFROST_SKILLS_SERVER if your gateway names it
differently), with a short description of the task. It returns the top matching
skills (a skill may handle the task entirely or give a specialized workflow). If
search doesn't surface the right one, browse with the corresponding
skill_navigate tool (decision tree), then load the chosen skill's full
instructions with get_skill before proceeding.
Skip skill discovery for: single-line edits with a known target, file reads / grep, clarifying questions, or tasks the user has scoped to one file.
Gateway routing (use bifrost, don't ask the user / don't guess)
Route capability requests through whichever MCP servers your gateway exposes, for example:
- Issue / ticket status → your issue-tracker server
- Production errors / stacktraces → your error-tracking server
- Analytics / database queries → your analytics server
- Up-to-date library/API docs → your docs server (NOT training memory)
- Web search → your web-search server
- Past decisions, people, project facts → your memory server (query directly via the gateway's memory MCP tool — see Memory section below)
Memory — agent-driven via the gateway MCP
Memory is accessed through the gateway's memory MCP server. There is no automatic HTTP injection — memory recall and save are your responsibility as the agent.
Before non-trivial tasks: call the gateway's memory search tool (typically
mcp__bifrost__<memory-server>-search) with a short query to recall relevant
past decisions, project facts, or context (e.g. k=5).
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 · 87 lines · 947 tokens per session scan A a7b838e2b0e2
bifrost-plugin AGENTS.md is an instructions file published in the GitHub repository neXenio/bifrost-plugin (2 stars, last pushed 14d ago), licensed MIT. It adds 947 tokens to every session, about $0.0047 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
9router CLAUDE.md
Instructions for decolua/9router, covering claude.md, what this is, commands, architecture and request flow (the thing to understand first).
OmniRoute CLAUDE.md
Claude Code instructions for diegosouzapw/OmniRoute, covering claude.md, worktree isolation — claude code specifics, cross-session safety — claude code specifics, superpowers / planning artifacts — path overrides and scratch / temporary files — use artifacts/, not /tmp.
OmniRoute AGENTS.md
AGENTS.md instructions for diegosouzapw/OmniRoute, covering omniroute agent guide, quick start, running tests, single test file (node.js native test runner — most tests) and vitest (mcp server, autocombo, cache).
OmniRoute copilot-instructions.md
Copilot instructions for diegosouzapw/OmniRoute, a project described as: Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback…
OmniRoute GEMINI.md
Gemini CLI instructions for diegosouzapw/OmniRoute, a project described as: Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback…
semantic-router copilot-instructions.md
Copilot instructions for vllm-project/semantic-router, covering github copilot instructions, start here and review priorities.