Agent harness benchmark (2026-09-10, anthropic claude-opus-5)One published run of the agent harness benchmark, the controls first, then cost-of-pass, paired deltas and pass rates. Generated from the committed report. Agent harness benchmark (2026-09-10, anthropic claude-sonnet-5)One published run of the agent harness benchmark, the controls first, then cost-of-pass, paired deltas and pass rates. Generated from the committed report. Agent skillsEvery skill magus installs, in both curated forms, generated from the embedded bodies. AgentsHow magus equips AI agents - the installable skills, the MAGUS.md routing index, the MCP server, and the guard hook any agent host can wire, with a setup page per host. Any other hostThe host-neutral contract - install the guidance where your host reads it, pipe the event to magus session hook, render the verdict with -o template - for an agent host magus does not document by name. Attention hooksmagus session notify turns one host event into a desktop notification, so a blocked or finished agent reaches you - and why this is a hook sink rather than an MCP tool. BenchmarksWhat magus measures about itself and publishes: the agent harness benchmark (does the agent surface make an agent cheaper or better on a real repository) and the build-tool comparison, with every run's environment stamped beside its numbers. Claude CodeWiring magus into Claude Code - skills in .claude/skills, the two PreToolUse guard hooks, attention notifications, and the checks that prove the guard is running. CodexWiring magus into Codex - skills in .agents/skills, the AGENTS.md block you paste, MCP in the user-level config, and the hooks that carry the guard, the checkpoint and the post-compaction brief. CursorWiring magus into Cursor - AGENTS.md for guidance, one self-contained hook script for all five of its events, and the one job Cursor's contract cannot express. DoctrineThe standing design decisions: the principles magus is built by, the standard it is measured against, and the line between what it automates and what it leaves to your judgment. Guard hook templatesThe hook templates Claude Code and Codex run for the magus guard, the checkpoint and the post-compaction brief, in POSIX sh and in Buzz - the variables that adapt them to a host, the version marker that tells you when your copy is stale, and the full source of each. Jobs and leasesThe surface magus gives an agent that fans work out - the working-state checkpoint, the declared job store, the lease a holder takes on a job, the console Jobs view, the recorded spawn, and verifying a result against the diff since the checkpoint. MCPmagus serves its tools as a Model Context Protocol server, over stdio for the agent host that launches magus mcp, or over Streamable HTTP from magus server. MGS1045: a magus\guard.spawn, command or write registration is unusableFires when magus\guard.spawn, magus\guard.command or magus\guard.write is handed something other than a function, is called twice in one load, or is called from a magusfile other than the root one. The workspace does not load. MGS3018: a directory as a job write pathFires when a job is forked with a write path that names an existing directory that is not a project root. The fork is refused; declare the files the job will edit, or the root of the project it owns whole. MGS3024: a hook names no agent hostInstalled hook glue called magus without --agent-name, so magus cannot tell which agent host it is answering. The call is refused, and `magus agent harness apply` rewrites a configuration that names the host. MGS3031: a declaration claim nothing can gradeFires when a job is forked with a write path that claims one declaration of a file (path#declaration) and no footprint could ever check it. The fork is refused; claim the whole file, or give its extension a diff driver. OpenCodeWiring magus into OpenCode - skills in .opencode/skills, the TypeScript plugin that carries both guard surfaces, the post-compaction brief, and the idle checkpoint. Quick startEverything you need to be productive with magus on one page - install, first target, the output flags, the agent skills and the guard hook - each linking to the page that goes deeper. Session load adaptersPer-host adapters that turn an agent host's own session log into the magus session event contract, so an audit can ask which skills loaded, whether the guard fired, and what ran unjudged. SkillsInstalling the magus agent skills - where each host reads them, the short primary and its always-full twin, the AGENTS.md block magus prints but never writes, and the drift check that grades what is installed. The guardWhat magus session hook denies, what it explains, and why - the four deny triggers, the file-path surface, the verdict contract a host wires into, and the observations magus records. magus agentRender agent skills, adapt a user-owned harness, or review recurring guard feedback; it never writes the AGENTS.md you own. magus jobThe POSIX child lifecycle over delegated work: fork declares a job, exec takes the lease on it in this checkout, exit returns it with its result, wait verifies that result, and run submits one of the server's own jobs. magus memoryManage the per-repository memory that lives outside the checkout: named entries people and agents can read across sessions and worktrees. magus sessionOne family over the repository's session store: list what magus invocations ran and the host session each ran in, list the blocks agents raised, close one by hand, and take the host-hook ingest that writes it all. magus-architecture-reviewGround refactoring and structure proposals in the magus knowledge graph instead of intuition. magus-buzz-reviewReview Buzz code - a magusfile, a spell, or a standalone .buzz script - across three lenses run in parallel: idiom/style, skeptic/correctness, and upstream-Buzz conformance. magus-buzz-writeWrite and run Buzz, the language magusfiles, spells, and `magus buzz` scripts are written in. magus-change-summarySummarize what changed in a magus workspace, write it up, or answer a granular diff question. magus-commit-compositionRestructure an UNPUSHED branch so each commit is one reviewable idea, using the workspace's own boundaries (project ownership, declared outputs, blast radius) rather than guessing from paths. magus-context-auditAudit the instructions an agent was given - the repo instruction file, installed skills, memory entries, a routing index, hook-injected text, and any user-level instruction file - for statements that contradict each other or that no longer match what the tools do. magus-docs-lookupTraverse magus's own documentation to answer a "how does magus do X / what does Y mean / where is Z documented" question, instead of guessing an answer or a URL. magus-memoryMaintain a user-owned per-repository memory through magus_memory or `magus memory`: named decisions, plans, pointers, and the hypotheses an investigation ruled out, all surviving worktrees and sessions. magus-multi-agentSplit work across agents in a magus workspace as an acceptance-criteria loop: partition by WRITE SET using graph evidence (magus refs --occurrences, explain, affected --plan --stdin), prove the leases cannot collide, narrow the scope at every level, and match each lease's model to the work it needs. magus-queryQuery the magus knowledge graph to find and relate entities (projects, targets, spells, ops, charms, modules, diagnostics, docs). magus-runRun builds, tests, lints, and codegen through magus targets. magus-sdkHelp a Go developer consume magus as a library (import "github.com/egladman/magus") instead of shelling out to the CLI, and audit whether the SDK actually serves them. magus-test-designChoose unit, integration, or end-to-end test boundaries from the magus graph and runtime behavior. magus-vcs-hygieneSafe version-control operations in a magus workspace (any repo with magusfile.buzz at the root). magus-workspace-rulesAdapt magus's installed agent surface to THIS workspace without breaking it. magus\guard.commandRegister one Buzz function the agent guard calls on every agent shell command, to add a deny or an advisory from your repository's own rules. magus ships the seam and no rules. magus\guard.spawnRegister one Buzz function the agent guard calls on every subagent spawn and continuation, to add a deny or an advisory from your own rules. magus ships the seam and no rules.