Skip to content

YujunZhou/tellonce / codex

tellonce

Verified

Use to view, explain, correct, delete or reorganize the user's saved preferences, or to record one by hand when automatic recording is off; learning and rule injection otherwise run automatically through Codex hooks.

FileKindSize
.codex-plugin/plugin.jsonconfig1.3 KB
SKILL.mdskill md12.0 KB
dashboard.shexecutablescript348 B
docs/CC_PARITY_MATRIX.mdmarkdown7.3 KB
docs/README.mdmarkdown3.4 KB
doctor.shexecutablescript345 B
hooks/hooks.jsonconfig714 B
hooks/posttooluse-deterministic-block.shexecutablescript2.0 KB
hooks/sessionstart-init.shexecutablescript1.9 KB
hooks/userpromptsubmit-dispatch.pyscript2.6 KB
hooks/userpromptsubmit-memory-upsert.shscript326 B
hooks/userpromptsubmit-pending-inject.shexecutablescript2.0 KB
hooks/userpromptsubmit-retrieve-inject.shexecutablescript3.1 KB
hooks/userpromptsubmit-shadow-alert-inject.shexecutablescript1.2 KB
install.shexecutablescript13.9 KB
shared_lib/_install_merge_settings.pyscript12.1 KB
shared_lib/_pt_hooks.txtmarkdown407 B
shared_lib/correction_interpretation.pyscript8.5 KB
shared_lib/detect_user_prefer.pyscript7.2 KB
shared_lib/deterministic_block.pyscript9.3 KB
shared_lib/event_obligations.pyscript19.8 KB
shared_lib/execution_support.pyscript75.8 KB
shared_lib/fingerprints.yamlconfig1.1 KB
shared_lib/learning_policy.pyscript4.6 KB
shared_lib/memory_judge.pyscript84.8 KB
shared_lib/memory_publication.pyscript14.9 KB
shared_lib/memory_runtime.pyscript12.2 KB
shared_lib/memory_store.pyscript99.6 KB
shared_lib/memory_upsert.pyscript57.1 KB
shared_lib/memory_upsert_hook.pyscript4.6 KB
shared_lib/model_requests.pyscript5.8 KB
shared_lib/path_config.pyscript13.3 KB
shared_lib/pending_queue_manager.pyscript23.4 KB
shared_lib/pt_platform.pyscript1.5 KB
shared_lib/redaction.pyscript3.4 KB
shared_lib/retrieve_inject.pyexecutablescript57.9 KB
shared_lib/rule_selection.pyscript18.9 KB
shared_lib/shadow_alert_inject.pyscript6.1 KB
shared_lib/training_memory.pyscript17.8 KB
shared_lib/transcript_adapter.pyscript13.7 KB
shared_lib/verify_compliance.pyexecutablescript24.5 KB
shared_lib/verify_retry_shadow.pyscript27.4 KB
tellonce_codex/__init__.pyscript52 B
tellonce_codex/__main__.pyscript49 B
tellonce_codex/cli.pyscript6.8 KB
tellonce_codex/codex_posttooluse_block.pyscript11.2 KB
tellonce_codex/dashboard.pyscript3.4 KB
tellonce_codex/doctor.pyscript10.9 KB
tellonce_codex/index.pyscript1.8 KB
tellonce_codex/install.pyscript3.1 KB
tellonce_codex/install_codex_hooks.pyscript15.1 KB
tellonce_codex/ledger.pyscript17.1 KB
tellonce_codex/memory.pyscript5.3 KB
tellonce_codex/migrate.pyscript1.3 KB
tellonce_codex/mode.pyscript2.3 KB
tellonce_codex/paths.pyscript8.6 KB
tellonce_codex/promote.pyscript4.4 KB
tellonce_codex/scan.pyscript2.6 KB
tellonce_codex/uninstall.pyscript1.7 KB
tellonce_codex/verify.pyscript5.3 KB
tellonce_codex/wrapper.pyscript12.0 KB
uninstall.shexecutablescript4.6 KB

tellonce_codex/scan.py

View on GitHub
from __future__ import annotations

from dataclasses import dataclass
import hashlib
from pathlib import Path

from .ledger import append_event, event_id, sanitize


@dataclass(frozen=True)
class ScanResult:
    signal_type: str
    event_id: str


def classify(message: str) -> str:
    """Heuristic classifier — kept simple on purpose.

    HX-6 fix: removed the single-character friction trigger that appeared
    as a substring inside many unrelated common words, which made friction
    over-fire on entirely unrelated messages. Replaced with disambiguating
    multi-character forms.
    """
    lowered = message.lower()
    # Heuristic seed tokens, language-neutral. We ship both English and Chinese
    # forms so the classifier fires for English-only and Chinese-speaking users
    # alike (the maintainer is a Chinese speaker; the public release targets
    # English users too). These are deliberately small, illustrative seed sets —
    # users extend behavior via their own fingerprints, not by editing this list.
    preference_zh = ["以后", "以后都", "必须", "不要", "我希望", "我想"]
    preference_en = ["from now on", "always", "never", "please don't", "i prefer", "i want", "make sure"]
    if any(token in message for token in preference_zh) or any(token in lowered for token in preference_en):
        return "preference"
    pitfall_en = ["again", "don't repeat", "frustrat"]
    if any(token in lowered for token in pitfall_en) or "又" in message:
        return "pitfall"
    friction_zh = ["很卡", "好卡", "太卡", "卡顿", "麻烦", "太慢", "血压"]
    friction_en = ["slow", "laggy", "annoying", "tedious", "keeps happening", "every time"]
    if any(token in message for token in friction_zh) or any(token in lowered for token in friction_en):
        return "friction"
    return "none"


def scan_message(state_root: Path, message: str, session_id: str = "codex-current", turn_id: int = 0) -> ScanResult:
    signal = classify(message)
    excerpt = sanitize(message[:200])
    eid = event_id(session_id)
    append_event(
        state_root,
        {
            "event_id": eid,
            "event_type": "scan_recorded",
            "session_id": session_id,
            "turn_id": turn_id,
            "payload": {
                "trigger": {
                    "excerpt_redacted": excerpt,
                    "content_sha256": hashlib.sha256(message.encode("utf-8")).hexdigest(),
                },
                "detection": {"signal_type": signal, "detected": signal != "none"},
            },
        },
    )
    return ScanResult(signal_type=signal, event_id=eid)
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: 472kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall