agent-system

A set of development rules for Grida's local daemon and AI-agent packages. The daemon handles local files, workspaces, secrets, and server access, while the agent handles sessions, providers, tools, prompts, and skills.

In plain words
What is it for?
Use it when editing the daemon or AI-agent packages, including server lifecycle, HTTP routes, sessions, workspaces, files, secrets, model providers, sandboxing, or tool execution.
Why use it?
It helps developers change these connected packages while preserving their boundaries and security rules. It also clarifies which package owns each part of the system.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gridaco/grida/agent-system
Any agent
npx skills add gridaco/grida --skill agent-system
Clone the repo
git clone --depth 1 https://github.com/gridaco/grida

Made for: Claude Code, Codex.

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00127 $0.03333
Opus 5 $0.00063 $0.01666
Sonnet 5 $0.00025 $0.00667
Haiku 4.5 $0.00013 $0.00333

Measured 2d ago against content hash e25ac8802b71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-system 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.

.agents/skills/agent-system/SKILL.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grida Agent System

This skill is for the two packages behind Grida Desktop and future hosts (issue #927): @grida/daemon — the local host layer (DaemonServer lifecycle, the loopback HTTP perimeter, files/recents/workspaces, the secrets store, daemon discovery, the tenant seam) — and @grida/agent — the agent TENANT mounted on it (sessions, providers, tool execution, prompt composition, skills, the AI-SDK stream contract). Dependency direction is one-way: @grida/agent imports @grida/daemon; the daemon is AI-free by contract (pinned by packages/grida-daemon/src/__boundary__.test.ts).

Use desktop for Electron shell work: BrowserWindow, menus, preload, native dialogs, file associations, deep links, and CDP verification.

Adjacent: sdk-design and sdk-seam for exported contracts and host seams, security when a change touches a GRIDA-SEC boundary.

When to use this skill

  • Editing packages/grida-daemon/** or packages/grida-ai-agent/**.
  • Changing DaemonServer lifecycle, the tenant seam, server capabilities, HTTP routes, transport, Basic Auth, Referer policy, sessions, workspaces/files, recents, secrets, BYOK providers, model tiers, sandbox policy, shell policy, runtime, tools, prompts, skills, or message streams.
  • Touching the desktop sidecar protocol because the daemon contract changed.
  • Debugging empty file lists, missing sessions, broken stream parts, provider resolution, tool-call behavior, or agent state recovery.
  • Editing renderer agent chat transport when the bug is in stream/session semantics rather than Electron bridge presence.

Skip this skill for BrowserWindow, menu, native dialog, file association, deep-link, packaging, or preload-only bugs. Use desktop for those.


Shape

Host adapter (Desktop today, other hosts later)
  - supplies auth material, workspace roots, entitlement hooks, sandbox wrapper
  - starts the composed daemon (createAgentDaemon) as sidecar or CLI daemon
        |
        v
DaemonServer (@grida/daemon/server)
  - loopback Hono perimeter (CORS -> Referer -> Basic Auth)
  - host capability routes: files, recents, workspaces + secrets store
  - the DaemonTenant seam (static typed list, not a plugin registry)
        |
        v
Agent tenant (@grida/agent/server — createAgentTenant)
  - AI route groups: /agent, /events, /sessions, /secrets, /providers,
    /images, /video
  - sessions SQLite, endpoint configs, runtime + run loop, stream registry
        |
        v
Runtime-agnostic agent core (@grida/agent)
  - protocol DTOs, prompts, tiers, skills, toolset, AI-SDK UI-message stream

Read the full file on GitHub · 307 lines

Changes

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.

  1. 2d ago First seen · 307 lines · 127 tokens per session scan A e25ac8802b71

Subscribe to this mod's changes

agent-system is a skill published in the GitHub repository gridaco/grida (2,629 stars, last pushed 12d ago), licensed Apache-2.0. It adds 127 tokens to every session and 3,333 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

react-hook-form

Correct React Hook Form usage anywhere in the monorepo — data flow, subscriptions, reset, dirty state, number inputs, and controlled-input rules. Load this BEFORE writing or modifying ANY form code, adding a field to an existing form, touching watch/useWatch/formState/getValues/setValue/reset, wiring a form into a…

supabase/supabase · 123 tokens

safe-sql-execution

Use whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix and never says "security," "injection," or "SafeSqlFragment." This covers: writing or editing any pg-meta function, query builder, or endpoint…

supabase/supabase · 221 tokens

studio-e2e-tests

Write and run Playwright E2E tests for Supabase Studio (e2e/studio). Use when asked to run e2e tests, write new E2E tests, or debug flaky or failing Playwright tests. Covers running commands, avoiding race conditions, waiting strategies, selectors, helper functions, and CI vs local differences.

supabase/supabase · 74 tokens

studio-mock-api-tests

Component tests for Supabase Studio that mock API requests at the network layer with MSW. Use when writing or reviewing a component test that exercises a React Query hook or mutation, or when migrating an existing test away from vi.mock('@/data/...'). Covers the customRender + addAPIMock template and the jsdom/MSW…

supabase/supabase · 79 tokens

ask-the-docs

Answer questions about the Supabase docs app (apps/docs) using documented architecture, build pipeline, and review-pattern notes, and apply feature-design principles (codebase reuse, coding minimalism) when proposing or critiquing changes. Use when the user asks "how does X work in the docs app?", "where does Y…

supabase/supabase · 129 tokens

clickhouse-logs-queries

Write, review, and migrate Supabase logs queries against the ClickHouse-backed logs table (the logs.all.otel analytics endpoint). Use this whenever a task involves Logs Explorer SQL, the logattributes map, querying a log source (edgelogs, postgreslogs, authlogs, etc.), translating an old BigQuery cross join…

supabase/supabase · 152 tokens