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/creative-int/sagu-plugins/agents-mdgit clone --depth 1 https://github.com/creative-int/sagu-pluginsWhat 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 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
sagu-plugins 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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sagu plugins — agent guide
Public distribution repo for Sagu: the sagu-dispatch and sagu-artifact
skills + plugin manifests for Cursor, Codex, and Claude Code, plus .mcp.json
and the MCP Registry server.json. Installable via
npx skills add creative-int/sagu-plugins and the three client plugin
marketplaces.
The one rule: generate, don't hand-edit
sagu.config.ts is the single source of truth. Every manifest, .mcp.json,
server.json, and the README install block are emitted from it by
tooling/generate.ts. Edit the config, then:
pnpm generate # rewrite all generated files
pnpm verify # check:generated (drift) + typecheck + MCP reachability smoke
Never hand-edit the generated files (.mcp.json, .claude-plugin/*,
.codex-plugin/*, .cursor-plugin/*, server.json, the README AUTO-GENERATED
block). CI runs check:generated and fails on drift.
To add a client
Add its install steps to installClients in tooling/generate.ts and, if it
needs a manifest, add the manifest builder to the files map. Regenerate.
Scope
- v0: two skills (
sagu-dispatch,sagu-artifact) + 3 client manifests +.mcp.json+server.json, generated. - v0.2 (deferred): optional stop hooks / knowledge-graph guardrails.
The MCP tool surface is hosted by the Sagu MCP server:
packages/mcp— local stdio server (npx -y @sagu/mcp,RADAR_API_KEY).apps/mcp— remote Streamable HTTP server (https://sagu-mcp.luke-nittmann.workers.dev/mcp).
Keep the agent-facing tool surface lean so it does not bloat context.
Platform posture
Tooling-only companion repo; no product runtime surface.
Companion plugin profile
This repo intentionally uses the agent-plugin-companion profile rather than the
full app-family turborepo profile. It is a public agent-facing distribution repo
for Sagu, so it owns generated plugin manifests, skills, MCP metadata, and
install documentation — not product runtime surfaces.
Required root contract for this profile:
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 · 65 lines · 706 tokens per session scan A 75447b17187f
sagu-plugins AGENTS.md is an instructions file published in the GitHub repository creative-int/sagu-plugins (0 stars, last pushed 1mo ago), licensed MIT. It adds 706 tokens to every session, about $0.0035 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.