akiiwa-games/AgentCompass / skills/agent-compass
agent-compass
FlaggedChoose 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.
scripts/cwd_policy.py
View on GitHub"""Account working-directory policy, shared by the allocator and model settings."""
import ntpath
from pathlib import Path
import re
def normalized(path=None):
"""The one form a directory is matched in: forward slashes, `.`, `..` and doubled separators resolved (so
`D:/work/app/../app2` is `D:/work/app2`, never inside `D:/work/app`), no trailing separator."""
return ntpath.normpath(str(path or Path.cwd())).replace('\\', '/').rstrip('/')
def validate(pattern):
value = str(pattern or '').strip()
try:
re.compile(value, re.IGNORECASE)
except re.error as error:
raise ValueError(f'Invalid directory regex: {error}') from None
return value
def matches(pattern, path=None):
try:
return not pattern or re.search(pattern, normalized(path), re.IGNORECASE) is not None
except (re.error, TypeError):
return False
def refusal(account, pattern, path=None):
"""The one sentence of an account whose `cwd_regex` does not match the directory it was matched against: the account,
the pattern, that directory and whose it is, and that the restriction is the user's own setting on this machine.
Callers add whether anything still launches."""
origin = "the worker's directory" if path else "this process's working directory"
return (f"account {account} is restricted to directories matching its cwd_regex {pattern!r} (the user's own "
f'account setting on this machine), and {origin} {normalized(path)} does not match')
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |