Funfigs
A local, file-based engineering framework for durable memory, structured software workflows, and daily briefings.
$30
Works with the AI Agents you already use
Funfigs
Example session with this skill installed
ff finish the user authentication module and update the shared memory with the final session timeout decision.
- Read your context and instructions
- Compiled the funfigs
I have completed the implementation of the user authentication module, including the neglected edge cases for session expiration, and updated the project memory.
Implementation & Memory Update
The authentication flow now correctly handles concurrent session limits and expired token redirects. I have recorded the 24-hour session timeout decision in the shared memory store.
Changes Summary
| Category | Details |
|---|---|
| Logic | Added SessionManager to handle sliding window expiration. |
| UI States | Implemented SessionExpiredModal and AuthLoadingSpinner. |
| Memory | Updated memory/projects/auth.md with timeout specs. |
| Index | Added link to auth specs in memory/MEMORY.md. |
// src/auth/session.config.ts
export const SESSION_CONFIG = {
timeoutMs: 86400000, // 24 hours as per project decision
renewalThresholdMs: 3600000,
maxConcurrentSessions: 3
};
Next steps
- Run
ff doctorto verify the new dependencies are correctly linked in the local environment. - Review the updated
memory/projects/auth.mdto ensure the session renewal logic matches the team's long-term requirements.
Connects securely to your tools. The creator never sees your data.
About this skill
You are managing a codebase where technical decisions, working rules, and project context are scattered across ephemeral chat histories or buried in Slack threads. Funfigs provides a local, file-based framework for engineering workflows and durable memory. It enforces a structured approach to software changes, architectural decisions, and daily planning without relying on proprietary cloud memory services.
What it does
- Standardize engineering by routing tasks through specific workflows for implementation, debugging, performance, and plan reviews.
- Maintain shared memory using a local Markdown-based store to track project decisions, facts, and persistent preferences across sessions.
- Import context from existing agent memory exports into a version-controlled, file-based index while filtering for privacy.
- Automate morning briefs by synthesizing calendar, message, and task data into styled, responsive HTML summaries.
- Enforce quality through a comprehensive library of 19 topic guides and 23 design-pattern recipes applied during code changes.
How it works
- Invoke workflows using
ffcommands to trigger specific engineering modes likeff finishfor UI states orff doctorfor setup health. - Access memory by reading from
memory/MEMORY.mdto ground answers in confirmed project facts. - Draft documents via the
docsskill to generate specifications or runbooks based on established repository constraints.
Frameworks & tools
This skill operates on local Markdown files, UTF-8 text, and HTML/CSS for visual briefs. It integrates with any development environment capable of reading local file systems, specifically optimized for Claude Code and Cursor users.
Why this beats prompting it yourself
Generic prompts forget project-specific rules and fail to maintain context across different agent instances. Funfigs provides a durable, versioned "source of truth" in your repository and forces the agent to follow proven engineering checklists instead of improvising.
Use cases
- Manage complex refactors by following the
Changesguide to ensure tests and migrations are handled. - Onboard new agents to a project by having them read the
shared/AGENTS.mdandmemory/directories. - Generate a visual daily agenda that combines calendar events with pending repository tasks.
- Capture architectural ADRs (Architecture Decision Records) using the
Decisionsworkflow.
Known limitations
Does not synchronize with private cloud memory databases or proprietary product histories. Scheduling recurring briefs requires host-specific scheduling tools. Requires local file system access.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Does not sync with cloud-private memory. Brief scheduling depends on host-specific tools. Requires local filesystem access for memory persistence.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 15 days ago
- Software
PythonBuilder MCP
Git