← All skills
loki-mode
67 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By davila7/claude-code-templates (GitHub) · coding · 33,256 stars · scanned at commit a6e6f93
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deplo…
Works with any agent that supports SKILL.md skills.
What this skill can do
Sends data to these websites: api.github.com, github.com
This is disclosed by the author in the skill's SKILL.md or README.
Found in 24 places.
Show 17 more
- cli-tool/components/skills/ai-research/loki-mode/INSTALLATION.md, line 80
curl -o ~/.claude/skills/loki-mode/references/agents.md \ - cli-tool/components/skills/ai-research/loki-mode/INSTALLATION.md, line 84
curl -o ~/.claude/skills/loki-mode/references/deployment.md \ - cli-tool/components/skills/ai-research/loki-mode/INSTALLATION.md, line 88
curl -o ~/.claude/skills/loki-mode/references/business-ops.md \ - cli-tool/components/skills/ai-research/loki-mode/INSTALLATION.md, line 258
wget -O ~/.claude/skills/loki-mode/SKILL.md \ - cli-tool/components/skills/ai-research/loki-mode/INSTALLATION.md, line 307
curl -o ~/.claude/skills/loki-mode/references/agents.md \ - cli-tool/components/skills/ai-research/loki-mode/autonomy/run.sh, line 690
const res = await fetch(path + '?t=' + Date.now()); - cli-tool/components/skills/ai-research/loki-mode/autonomy/run.sh, line 777
const state = await fetch('../state/orchestrator.json?t=' + Date.now()).then(r => r.json()); - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-24-17/swebench-patches/django__django-12915.patch, line 20
from urllib.request import url2pathname - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-24-17/swebench-patches/django__django-12915.patch, line 62
from urllib.request import url2pathname - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-24-17/swebench-patches/psf__requests-2674.patch, line 22
Looking at the models.py code, it already handles `DecodeError` properly in `iter_content`, wrapping it as `ContentDecodingError`. But the adapters.py `send` me - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-35-39/swebench-patches/django__django-12915.patch, line 21
from urllib.request import url2pathname - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-35-39/swebench-predictions.json, line 224
"model_patch": "Based on my analysis of the existing patches and the issue, I need to create a clean patch. The key insight is:\n\n1. `StaticFilesHandlerMixin` - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-01-35-39/swebench-results.json, line 232
"model_patch": "Based on my analysis of the existing patches and the issue, I need to create a clean patch. The key insight is:\n\n1. `StaticFilesHandlerMixin` - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 163
curl -sL "https://github.com/openai/human-eval/raw/master/data/HumanEval.jsonl.gz" | \ - cli-tool/components/skills/ai-research/loki-mode/examples/todo-app-generated/frontend/src/api/todos.ts, line 15
const response = await fetch(`${API_BASE}/todos`); - cli-tool/components/skills/ai-research/loki-mode/examples/todo-app-generated/frontend/src/api/todos.ts, line 23
const response = await fetch(`${API_BASE}/todos`, { - cli-tool/components/skills/ai-research/loki-mode/examples/todo-app-generated/frontend/src/api/todos.ts, line 37
const response = await fetch(`${API_BASE}/todos/${id}`, {
and 4 more places
Changes files outside its own folder
The author does not mention this.
Found in 10 places.
Show 7 more
Downloads and installs other software
The author does not mention this.
Found in 33 places.
Show 17 more
- cli-tool/components/skills/ai-research/loki-mode/autonomy/run.sh, line 168
log_info "Install: https://claude.ai/code or npm install -g @anthropic-ai/claude-code" - cli-tool/components/skills/ai-research/loki-mode/benchmarks/datasets/swebench-lite.json, line 8
"install_command": "pip install swebench", - cli-tool/components/skills/ai-research/loki-mode/benchmarks/results/2026-01-05-00-23-56/swebench-results.json, line 8
"install": "pip install swebench", - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 145
pip install -q requests tqdm - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 944
"install_command": "pip install swebench", - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 990
"install": "pip install swebench", - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1010
pip install -q swebench datasets - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1220
pip install -q swebench datasets - cli-tool/components/skills/ai-research/loki-mode/demo/README.md, line 79
brew install charmbracelet/tap/vhs - cli-tool/components/skills/ai-research/loki-mode/demo/record-demo.sh, line 26
echo "Install with: pip install asciinema" - cli-tool/components/skills/ai-research/loki-mode/demo/record-full-demo.sh, line 83
log_warn "ffmpeg not found. Install with: brew install ffmpeg" - cli-tool/components/skills/ai-research/loki-mode/demo/run-demo.sh, line 237
info "Run 'npx vibe-kanban' to view visual board" - cli-tool/components/skills/ai-research/loki-mode/integrations/vibe-kanban.md, line 20
npx vibe-kanban - cli-tool/components/skills/ai-research/loki-mode/references/deployment.md, line 21
npm i -g vercel - cli-tool/components/skills/ai-research/loki-mode/references/deployment.md, line 33
npm i -g netlify-cli - cli-tool/components/skills/ai-research/loki-mode/references/deployment.md, line 45
npm i -g @railway/cli - cli-tool/components/skills/ai-research/loki-mode/references/quality-control.md, line 408
npx prettier --write "$1"
and 13 more places
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 18 places.
Show 15 more
- cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 374
result = subprocess.run( - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 391
except subprocess.TimeoutExpired: - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 560
result = subprocess.run( - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 567
except subprocess.TimeoutExpired: - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 639
result = subprocess.run( - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 653
except subprocess.TimeoutExpired: - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1030
subprocess.run([sys.executable, '-m', 'pip', 'install', '-q', 'swebench', 'datasets']) - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1100
result = subprocess.run( - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1119
except subprocess.TimeoutExpired: - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1237
subprocess.run([sys.executable, '-m', 'pip', 'install', '-q', 'swebench', 'datasets']) - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1277
result = subprocess.run( - cli-tool/components/skills/ai-research/loki-mode/benchmarks/run-benchmarks.sh, line 1292
except subprocess.TimeoutExpired: - cli-tool/components/skills/ai-research/loki-mode/tests/test-agent-timeout.sh, line 44
gtimeout "$timeout_seconds" bash -c "$cmd" - cli-tool/components/skills/ai-research/loki-mode/tests/test-agent-timeout.sh, line 47
timeout "$timeout_seconds" bash -c "$cmd" - cli-tool/components/skills/ai-research/loki-mode/tests/test-agent-timeout.sh, line 55
' "$timeout_seconds" bash -c "$cmd"
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'loki-mode' ] || [ -L ~/.agents/skills/'loki-mode' ]; then echo 'A skill folder named loki-mode already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/davila7/claude-code-templates' "$d" && git -C "$d" checkout --quiet 'a6e6f93e9a4baaa6ff337aee5505bf5c2bae4ce6' -- 'cli-tool/components/skills/ai-research/loki-mode' && mkdir -p ~/.agents/skills && cp -R "$d"/'cli-tool/components/skills/ai-research/loki-mode' ~/.agents/skills/'loki-mode' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'loki-mode' ~/.claude/skills/'loki-mode' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for davila7/claude-code-templates shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/davila7/claude-code-templates/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | a6e6f93 | 67 |
| 2026-11-08 | b086f26 | 67 |
| 2026-11-07 | 395f30e | 67 |
Also found in
Identical copies of this skill exist at:
- Dicklesworthstone/pi_agent_rust/tests/ext_conformance/artifacts/templates-davila7/cli-tool/components/skills/ai-research/loki-mode