A multi-agent system for turning a product requirements document into a deployed software product. It coordinates specialised agents for engineering, testing, operations, security, data, and business tasks.

Use it to organise autonomous work on software projects, including development, quality checks, deployment, security, monitoring, marketing, and customer support.

It reduces the need to coordinate many development roles and track work across the stages from planning to deployment. It also keeps project state and lessons in files for later work.

loki-mode — Skill for Claude Code and Codex by davila7

About the project

Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.

davila7/claude-code-templates · 32,814 stars · on GitHub · aitmpl.com

Install

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.

Any agent

npx skills add davila7/claude-code-templates --skill loki-mode

Clone the repo

git clone --depth 1 https://github.com/davila7/claude-code-templates

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/davila7/claude-code-templates/loki-mode/github.svg)](https://agentmods.dev/skills/davila7/claude-code-templates/loki-mode)

Your own site

<a href="https://agentmods.dev/skills/davila7/claude-code-templates/loki-mode"><img src="https://agentmods.dev/badge/skills/davila7/claude-code-templates/loki-mode/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/davila7/claude-code-templates/loki-mode"><img src="https://agentmods.dev/badge/skills/davila7/claude-code-templates/loki-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,595 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Snyk pass 7 Sept 2026
NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 366
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 587
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.00152	$0.06595
Opus 5.5	$0.00061	$0.02638
Sonnet 5.5	$0.00030	$0.01319
Haiku 4.5	$0.00015	$0.00660

Measured 1mo ago against content hash d8a3e2e639a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loki-mode 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 1mo ago.

The scan reads SKILL.md. This mod also ships 46 executable files (autonomy/run.sh, benchmarks/prepare-submission.sh, benchmarks/results/2026-01-05-00-49-17/humaneval-solutions/0.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

cli-tool/components/skills/ai-research/loki-mode/SKILL.md · 722 lines

How it starts

The opening of the file, as written. The whole thing — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loki Mode - Multi-Agent Autonomous Startup System

Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Quick Reference

Critical First Steps (Every Turn)

READ .loki/CONTINUITY.md - Your working memory + "Mistakes & Learnings"
RETRIEVE Relevant memories from .loki/memory/ (episodic patterns, anti-patterns)
CHECK .loki/state/orchestrator.json - Current phase/metrics
REVIEW .loki/queue/pending.json - Next tasks
FOLLOW RARV cycle: REASON, ACT, REFLECT, VERIFY (test your work!)
OPTIMIZE Opus=planning, Sonnet=development, Haiku=unit tests/monitoring - 10+ Haiku agents in parallel
TRACK Efficiency metrics: tokens, time, agent count per task
CONSOLIDATE After task: Update episodic memory, extract patterns to semantic memory

Key Files (Priority Order)

File	Purpose	Update When
`.loki/CONTINUITY.md`	Working memory - what am I doing NOW?	Every turn
`.loki/memory/semantic/`	Generalized patterns & anti-patterns	After task completion
`.loki/memory/episodic/`	Specific interaction traces	After each action
`.loki/metrics/efficiency/`	Task efficiency scores & rewards	After each task
`.loki/specs/openapi.yaml`	API spec - source of truth	Architecture changes
`CLAUDE.md`	Project context - arch & patterns	Significant changes
`.loki/queue/*.json`	Task states	Every task change

Decision Tree: What To Do Next?

START
  |
  +-- Read CONTINUITY.md ----------+
  |                                |
  +-- Task in-progress?            |
  |   +-- YES: Resume              |
  |   +-- NO: Check pending queue  |
  |                                |
  +-- Pending tasks?               |
  |   +-- YES: Claim highest priority
  |   +-- NO: Check phase completion
  |                                |
  +-- Phase done?                  |
  |   +-- YES: Advance to next phase
  |   +-- NO: Generate tasks for phase
  |                                |
LOOP <-----------------------------+

Read the full file on GitHub · 722 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

1mo ago First seen · 722 lines · 152 tokens per session scan A d8a3e2e639a8

Subscribe to this mod's changes

loki-mode is a skill published in the GitHub repository davila7/claude-code-templates (32,814 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 6,595 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.

Building agents Claude Code Project management anthropic anthropic-claude claude

harness-step3-session-management

A project setup for keeping an agent’s work state in files between separate chat sessions. It creates a task list, a progress summary, and a script for checking the project environment.

simbajigege/book2skills · 149 tokens

ccc-fable

Arm, check, audit or disarm the Fable Method: the PM loop, 12 checkable gates, workflow-first posture and verifier separation, persisted in Commander state. Use when the user says fable on/off/status/audit or wants verification-gated, orchestrated work.

KevinZai/commander · 61 tokens

ccc-linear

View your open Linear issues, pick one to work on (moves it to In Progress and creates a branch), create a new issue, or see a board overview, all from pickers. Use when the user types $ccc-linear, asks for their Linear issues or tickets, or wants to start work from a ticket.

KevinZai/commander · 67 tokens

ccc-onboard

Contributor first-hour plan for the current repository: reads CLAUDE.md, BIBLE.md and package.json, checks required tools, asks the contributor's role, and returns a five-step checklist plus five real starter resources. Use when someone new joins a repo or types $ccc-onboard.

KevinZai/commander · 62 tokens

ccc-triage

Triage a GitHub repo's open issues and PRs with the gh CLI: flag stale, unlabeled and CI-failing items, propose labels and next actions, apply labels one confirmed item at a time, or summarize the backlog. Use when a maintainer asks to triage issues or PRs, label the backlog, or wants a digest.

KevinZai/commander · 76 tokens

ccc-smb-ops

Small-business back office from a bank CSV or a typed list: 13-week cash-flow forecast, invoicing and AR chasing, payroll planning, CRM cleanup, expense tracking, and a Monday owner brief. Use when an owner asks about cash, unpaid invoices, payroll, contacts, spending, or the weekly picture.

KevinZai/commander · 69 tokens