@event4u/agent Config
About
Universal AI Agent OS — governed skills, rules, and commands for AI coding assistants (Claude Code, Augment, Cursor, Copilot, Windsurf). Read-only MCP bridge serves prompts and resources from a release-pinned content bundle.
Details
- Author
- event4u-app
- Downloads
- 196
- Categories
- Developer Tools, AI
Jump to
- Read-only MCP bridge for prompts and resources.
- Uses a release-pinned content bundle.
- Governed skills, rules, and commands for coding assistants.
- Works with Claude Code, Augment, Cursor, Copilot, Windsurf.
What does “read-only MCP bridge” mean?
The server only serves (reads) prompts and resources; it does not accept changes or writes back to the content bundle.
Which AI coding assistants are supported?
The server explicitly works with Claude Code, Augment, Cursor, Copilot, and Windsurf.
How are prompts and resources stored and versioned?
They are delivered from a release-pinned content bundle, meaning each version of the bundle is fixed at a specific release.
What transport protocol does the server use?
The server implements the Model Context Protocol (MCP), but the specific transport (e.g., stdio, HTTP) is not detailed in the README.
Are there any authentication or permissions?
No authentication or permissions are mentioned; the server is designed as a read-only bridge with no user-configurable access controls.
Agent Config — every claim machine-checked, including "zero runtime daemon"
Try it in 30 seconds— drop one read-only subagent into any repo and watch it gate "done":@production-validator check this branch is actually done. No wizard, no lock-in, nothing else installed — the30-second wedge ↓is the whole first step. Start at the proof, not the catalog:event4u-app.github.io/agent-config/proof/.
Every public claim in this README is machine-checked —verify it yourself.In a market that runs on unbacked headline numbers, this one binds each claim to resolvable evidence or fails its own build.
Choose your experience — developer · founder · content · agency · finance · ops. Add packs. Get a focused command set, not a 500-artefact dump.Bring your own AI provider.
A deep library of skills, commands and governed rules— plus a capability router that loads the right skill on intent and multi-agent orchestration with consensus review. The whole layer is compiled into20 host agents— of 23 detected, 3 being export-only<!-- --> (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini CLI, Codex, Continue, Zed, JetBrains, Aider and more) — withzero runtime daemon.<!-- --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
It is both deepanddisciplined — and honest about what it deliberately is not:
- Depth that routes itself— a deep skill and command library, with a capability router that loads the right one on intent, not a 500-artefact context dump.
- Governance on every host— rules compiled into each tool's native format at projection time; deterministic runtime hooks added on hook-capable hosts. This config-space, host-agnostic governance is the moat (the governance advantage·enforcement by host).
- Surgical uninstall— removes only its own keys from a shared host config (matched by JSON-pointer + SHA-256), never a neighbour tool's entries.
- Pack-scoped install— writes the active pack only, not a 500-artefact dump.
What it deliberately isnot— the core is a governance layer with optional, individually opt-in embedded engines (code intelligence, gated reach, the setup GUI, the bench lab —ADR-124):no background daemon, no separate state database, no self-rewriting memory, no auto-build pipeline.Engines are never mandatory, never default-on without measured lift, and terminate with the command that invoked them. The host agent runs the loop; every learned change is human-reviewed; the same layer stays portable across tools. Capability without a process to babysit.
Where this comes from (honest provenance).The skills, rules and personas are distilled from real production work on TypeScript and PHP codebases. The governance mechanics are stack-agnostic, but the domain heuristics are richest where they were forged — treat coverage on other stacks as promising, not proven and tell us where it falls short.
See exactlywhat works on which hostor jump tothings you can do in a minute.
agent-config setupwritesprofile.idto.agent-settings.yml; each anchor below is the first-screen the wizard sends you to. One README, six entries, no role-detection guesswork.
Not sure which one?Runnpx @event4u/agent-config initthenagent-config setup— the browser wizard asks a single 8-option role question and maps to the closest profile. Source-of-truth:src/agent-src/profiles/· schema:docs/contracts/profile-system.md. Beyond software:user-types/(galabau · metalworking · truck — seeBeyond software.
Per-profile experience pages(who it's for · first tasks · packs + flows · what isnotloaded · examples):developer·content_creator·founder·agency·finance·ops.
You don't memorize every command — you run awork journey. Four flows span the developer story end-to-end; each names the command you TYPE to start and the skills it composes:
Full detail — entry commands, canonical path, composed skills per flow:docs/flows.md. (agent-admin— memory / analytics / config — is platform operation, not a user-work flow.)
CHANGELOG·Upgrade to 6.0·Breaking changes·Latest release·Discussions
Distribution:npm install @event4u/agent-config. Major bumps followsemver; each ships a### Breakingentry — all majors indexed inBREAKING_CHANGES.md.
Creative Pack — cinematic AI video.script → character-locked image → motion+audio prompt → provider render → stitched clip, withAIV_DRYRUN=trueas the cost-safety default. A first-class capability inside thecontent / creatorexperience — no longer the package's headline. See/video:from-script.
Legal Pack — not legal advice.The EU/DE legal pack (contract/NDA/DPA review, triage) is aresearch-and-drafting aid only— it does not provide legal advice, does not replace a qualified lawyer and must not be relied on for any concrete matter. It produces general information and general templates, never individual-case examination. ReadLEGAL_NOTICE.mdbefore use.
Full catalog — every skill, rule, command, guideline:docs/catalog.md. The headline is theexperience(profile + packs)andthe depth behind it.
Run from a consumer repo — bootstrap vianpx, the agent picks up your stack and you ship work end-to-end. New install? Start with theQuickstart. Already installed?Supported toolsshows the wired AIs;docs/featured-commands.mdlists the end-to-end workflows (/implement-ticket,/work,/commit,/pr:create). Deeper tour:2-minute demo.
Install scope.Pickonescope per machine — project-local (default, recommended for application repos) or user-global (recommended for tooling repos / dotfiles). The installer refuses a second, conflicting scope via thescope_guardpre-flight. Details:docs/contracts/install-scopes.md. Cleanup when needed:bash src/scripts/cleanup_other_scope.sh --confirm.
Don't take the claims on trust —verify them.docs/proof.mdis generated from source: a claim→evidence table (every public claim binds to a resolvable pointer or CI fails), honest-null benchmarksincluding the runs where the package changed nothingand a "verify it yourself" block you run on a fresh checkout. The proof page fails CI if it drifts from its sources — reproducibility is the proof. Browse it on the deployed docs site — the proof page is the primary entry:event4u-app.github.io/agent-config/proof/. The honest comparison frame lives atdocs/us-vs-the-category.md. Freshest measured row: in one post-fix session, advisory context injection cut language-mirror violations 555 → 19 while the two blocking guards went 8 → 0 and 1 → 0 — advisory reduced massively, only blocking eliminated. One session and a post-hoc reading, so a recorded prior rather than a law.
Maintaining a skills catalog yourself? Theanti-reskin gatethat blocks find-replace re-skin PRs here runs on your catalog too —docs/anti-reskin-gate.md.
Audit-disciplined by construction — every memory consult, decision key and hook concern lands inagents/runtime/state/so you can replay it.Core principlesnames the four invariants;Whatagent-configis — and what it isn'tdraws the scope boundary.
Working on the package itself?Developmentcovers thetask cipipeline,Requirementsthe toolchain,Maintainer telemetrythe opt-in measurement loop. Source-of-truth tree issrc/(src/skills,src/rules,src/agent-src/); never hand-edit.augment/ordist/agent-src/.
Security.Disclosure policy:SECURITY.md. Threat model:docs/threat-model.md.
Try one thing in 30 seconds— before the full suite, drop in a single self-contained subagent and see the discipline on your own repo:
mkdir -p .claude/agents curl -fsSL https://raw.githubusercontent.com/event4u-app/agent-config/main/docs/wedge/production-validator/production-validator.md \ -o .claude/agents/production-validator.md # then in Claude Code: @production-validator check this branch is actually done
production-validatoris read-only and installs nothing else — it gates "done" by hunting mocks/stubs on the shipped path and demanding real-system evidence (what it does). Like it? Install the full suite:
One command. Detection-driven — your installed AI tools are found and pre-selected. Nothing is written until you click Finish. No YAML by hand.
Those four are structural: they hold on every run, because they are properties of the code path rather than of your machine. Howlongit takes is not one of them — that is dominated by network and registry latency, which we do not control. The install →doctorwall-clock is measured by CI on every umbrella run and published with its conditions, as evidence; it is never a promised number.
# 1. Install — on a terminal with a display, the browser wizard launches # automatically; the same TypeScript installer runs the real install behind it. npx -y @event4u/agent-config init # 2. Pick your profile + tools in the wizard, click Finish. # (Writes ~/.event4u/agent-config/, ~/.claude/, ~/.cursor/, …) # 3. First real task — agent refines, plans, verifies. /work "your first real task"
Headless / CI:initskips the GUI automatically on CI, on a non-TTY, on a headless host, and whenever any CLI-mode flag is present — it then runs the non-interactive installer directly. The full opt-out set is listed once, against the code, ingui-wizard§ When the GUI is skipped. Pass flags (--profile=balanced --tools=claude-code,cursor); add--dry-runto preview writes. The GUI and the CLI share one installer (src/scripts/install.ts), so both produce identical results. Reference:docs/wizard.md.
Pick specific AIs:--tools=claude-code,cursor,augment,windsurf,cline,gemini-cli,copilot,roocode,aider,codex,claude-desktop,continue(any subset). Visual picker: add--gui(loopback-bound, CSRF-gated; contractgui-wizard).--guiis an opt-in that forces the wizard past the TTY and headless checks — it doesnotoverrideCI,AGENT_CONFIG_NO_UI, or a CLI-mode flag; combining it with one of those exits non-zero rather than quietly running the CLI install. On a headless host add--allow-headlessand connect a browser to the printed URL.
Verify hook coverage:npx @event4u/agent-config hooks:statusprints the per-platform matrix (--strictfor CI,--format jsonfor tooling).
Scope (v2.5+):initwritesglobalonly —~/.event4u/agent-config/,~/.claude/,~/.cursor/, …. The project tree getsagents/overrides/only (the bridge marker was retired — ADR-020 amendment 2026-07-13; the global root resolves from~/.event4u/agent-config).--projectis maintainer-only behindAGENT_CONFIG_DEV_MODE=1(ADR-020,dev-mode).
Migrating from a v1.x install?npx @event4u/agent-config migrate— full notes in[docs/migration/v1-to-v2.md.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
