Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/alphaaiservice/cortex/feature-flagsgit clone --depth 1 https://github.com/alphaaiservice/cortexWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.05569 |
| Opus 5 | $0.00020 | $0.02785 |
| Sonnet 5 | $0.00008 | $0.01114 |
| Haiku 4.5 | $0.00004 | $0.00557 |
Grade A, and why
feature-flags scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flag System
Action: $ARGUMENTS (default: init)
Parse $ARGUMENTS:
init— Generate the complete feature flag system (DB schema, service, API, admin UI)create <flag-name> [--description "..."] [--rollout 0-100]— Create a new feature flaglist— Show all flags with status, rollout %, and usage statstoggle <flag-name> [--env staging|production] [--on|--off]— Toggle a flagcleanup— Find and remove stale/fully-rolled-out flags from code- No argument =
init
Step 0: Detect Project Context
echo "=== Project Type ==="
ls package.json pyproject.toml build.gradle.kts pom.xml 2>/dev/null
echo "=== Backend Language ==="
if [ -f "pyproject.toml" ] || [ -f "requirements.txt" ]; then
echo "Python/FastAPI detected"
elif [ -f "package.json" ] && grep -q "nestjs" package.json 2>/dev/null; then
echo "NestJS detected"
elif [ -f "build.gradle.kts" ] || [ -f "pom.xml" ]; then
echo "Spring Boot detected"
fi
echo "=== Existing Feature Flags ==="
grep -rn "feature.flag\|feature_flag\|FeatureFlag\|FEATURE_" --include="*.py" --include="*.ts" --include="*.java" . 2>/dev/null | grep -v node_modules | head -20
echo "=== Database ==="
grep -rn "mysql\|DATABASE_URL" .env* 2>/dev/null | head -5
grep -rn "redis\|REDIS" .env* 2>/dev/null | head -5
Step 1: Database Schema (Action: init)
MySQL Migration
Generate the feature flags table migration.
Python (Alembic):
"""create feature flags tables
Revision ID: xxxx
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects.mysql import JSON
def upgrade() -> None:
op.create_table(
'feature_flags',
sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
sa.Column('name', sa.String(100), nullable=False, unique=True, index=True),
sa.Column('description', sa.Text(), nullable=True),
sa.Column('enabled', sa.Boolean(), default=False, nullable=False),
sa.Column('rollout_percentage', sa.Integer(), default=0, nullable=False),
sa.Column('conditions', JSON, nullable=True), # {"roles": ["admin"], "user_ids": [1,2,3], "regions": ["IN"]}
sa.Column('kill_switch', sa.Boolean(), default=False, nullable=False), # True = force OFF regardless
sa.Column('stale_after', sa.DateTime(), nullable=True), # When this flag should be reviewed
sa.Column('created_by', sa.String(100), nullable=True),
sa.Column('created_at', sa.DateTime(), server_default=sa.func.now(), nullable=False),
sa.Column('updated_at', sa.DateTime(), server_default=sa.func.now(), onupdate=sa.func.now(), nullable=False),
sa.PrimaryKeyConstraint('id'),
)
op.create_table(
'feature_flag_overrides',
sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
sa.Column('flag_id', sa.Integer(), sa.ForeignKey('feature_flags.id', ondelete='CASCADE'), nullable=False),
sa.Column('user_id', sa.Integer(), nullable=True),
sa.Column('role', sa.String(50), nullable=True),
sa.Column('enabled', sa.Boolean(), nullable=False),
sa.Column('created_at', sa.DateTime(), server_default=sa.func.now(), nullable=False),
sa.PrimaryKeyConstraint('id'),
sa.UniqueConstraint('flag_id', 'user_id', name='uq_flag_user'),
)
op.create_table(
'feature_flag_audit_log',
sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
sa.Column('flag_id', sa.Integer(), sa.ForeignKey('feature_flags.id', ondelete='CASCADE'), nullable=False),
sa.Column('action', sa.String(50), nullable=False), # created, enabled, disabled, rollout_changed, deleted
sa.Column('old_value', sa.Text(), nullable=True),
sa.Column('new_value', sa.Text(), nullable=True),
sa.Column('changed_by', sa.String(100), nullable=True),
sa.Column('changed_at', sa.DateTime(), server_default=sa.func.now(), nullable=False),
sa.PrimaryKeyConstraint('id'),
)
def downgrade() -> None:
op.drop_table('feature_flag_audit_log')
op.drop_table('feature_flag_overrides')
op.drop_table('feature_flags')
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 654 lines · 41 tokens per session scan A 0acadb539355
feature-flags is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 41 tokens to every session and 5,569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
alfred
Asistente contextual de Alfred Dev. Enruta automáticamente al flujo o comando operativo correcto.
feature
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega.
_composicion
Protocolo interno compartido para la composición dinámica del equipo de Alfred según tarea, stack y señales runtime.
ajustes
Configura Alfred Dev: autonomía, proyecto, Lucius, memoria y personalidad. Antes /alfred-dev:config.
audit
Auditoría completa del proyecto con 4 agentes en paralelo.
discuss
Refina una idea o feature antes de abrir un flujo completo de implementación.