Skip to content

akiiwa-games/AgentCompass / skills/agent-compass

agent-compass

Unverified

Choose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local usage and effective account policy, profiles the task with the configured System-One scorer, then allocates a compatible worker. Use for independent worker or advisor work; ordinary local execution needs no routing.

AgentCompass

Execution ownership

The main session executes serial work directly by default, including ordinary investigation, edits and verification. Duration, tool-call count and reading multiple files are not reasons to delegate. Delegate when independent work benefits from parallelism, isolation of a large context, a specialist capability or quota offloading. The main session is the only coordinator. Before writing any brief, list the separate tasks in the work (one deliverable each, with what it waits on): keep the tasks coupled to the conversation, write one brief per independent task, and roll them together; never hand several tasks to one worker to coordinate. Start a task that needs another's result after that result returns. Parts that each wait on the one before are one serial task: do it yourself or roll it as one brief. Send follow-up or related work to the worker that already holds the context: use send_agent_prompt while its continuation verdict says same worker, or roll --resume <id> (passing the same --workspace also matches an idle worker there). If routing itself is broken, diagnose and repair it directly. A delegated worker (AGENTCOMPASS_WORKER=1 or a Parent session agent ID: contract) executes its assignment without further delegation unless explicitly appointed coordinator.

Dispatch

To delegate work to a subagent, worker or advisor, run one command; the router picks the model, launches the worker and returns what to do next:

agentcompass roll --task "<what the worker should do>"

Before you launch, continue or replace a worker, read the dispatch rules: model and effort overrides, re-rolling an unavailable owner, the configured context rotation threshold (rotate_after_carried_tokens, set in the tray), permission modes, the gate and record, and parent messaging.

Long or multi-line assignments: --task - reads stdin, --brief <file> reads a file; the worker always gets your text unchanged. Several single-task briefs go in one call, --brief a.md --brief b.md: they are classified at the same time and routed one after another (status: batch, one result per brief). Do not call create_agent, Agent, spawn_agent, invoke_subagent or a CLI yourself.

agentcompass is the only entry and works from any directory; do not run files under scripts/. Installed package (uv tool install / pip install): type it as shown. Source checkout without an install: python -X utf8 <checkout>/agentcompass roll ... (the same arguments; your global agent rules spell the absolute path). agentcompass -h lists the commands, agentcompass <command> -h shows the options of one.

Read status in the result and do exactly next_action: launched = start nothing else (next_action says how the result arrives; when it says completion arrives as a notification, finish any independent work and end your turn to wait for it — never sleep or poll paseo ls, get_agent_status or result files in a shell command), pending = run next_argv, never roll again, split = the classifier reads the brief as several separate tasks (task_count): split it yourself, roll one brief per independent task and do the coupled ones yourself; if it truly is one assignment, roll it again with --keep-whole "<why>" (the daily audit reviews these reasons), self / native / blocked / error = follow next_action (blocked with blocked_by = that --workspace already has a writer; blocked with caller_action: "wait_for_reset" = you passed --can-wait-hours and the task should wait start_after_hours for a stronger model's quota window to reset before rolling again; see the dispatch lifecycle). The full result is at details (or print it with --verbose).

Optional, only when true (agentcompass roll -h): --workspace <dir>, --hours <n>, --can-wait-hours <h> (only when the work is not urgent: how many hours it may wait for a stronger model's quota window to reset; without it, roll launches the best model that can start now), --local-only "<dependency>" (only when no --workspace is given; --workspace already implies local work), --keep-whole "<reason>", --new-worker, --resume <agent_id>, --file <path>, --apply-to <path>, --fast, and for a user-named model --provider/--account/--model/--effort --basis "<user quote>".

Herdr core auto-detects its actual terminal. Read Herdr first-time setup and support limits for installation and completion collection. Raw shell roll in Cindy is refused; the Cindy plugin is a separate repository (cindy-agentcompass-plugin).

Troubleshooting after an update: if local state under ~/.agent-compass, hooks or global rule blocks fail with an old-shape error, run agentcompass doctor and apply the printed fix (re-run "agentcompass setup", an edit the message names, or delete "<file>" with what it discards).

More: dispatch rules · roll reference (result variants, Dot/Grok/CLI/native) · router internals (when to delegate, plan and record, scoring, launch contract, reference index).

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall