projects

A project system that groups a folder with its default settings, saved sessions, name, and icon. The folder becomes the working directory where the agent runs and accesses files.

In plain words
What is it for?
Use it to organize agent work by codebase or task, set its working folder and defaults, and manage its associated sessions.
Why use it?
It gives each group of work a consistent place, configuration, and conversation history instead of mixing unrelated tasks together.

Agent

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.

agentmods
npx agentmods add agents/yogasw/wick/projects
Clone the repo
git clone --depth 1 https://github.com/yogasw/wick
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,179 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04179
Opus 5 $0.00000 $0.02090
Sonnet 5 $0.00000 $0.00836
Haiku 4.5 $0.00000 $0.00418

Measured yesterday against content hash 8d20a6e008a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

projects 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.

docs/guide/agents/projects.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Projects

A project bundles a folder with its defaults. One project = 1 folder + defaults + pinned sessions + a display name and icon. Sessions belong to a project; the project's folder is the cwd the agent subprocess runs in.

The agent runs as a subprocess; the project's folder is the cwd it gets. Whatever you (or the agent itself, via Bash) put in the folder is the agent's world.

::: info Source Code: internal/agents/project/project.go (Meta, CRUD, ResolvePath). Migration from the old workspace model: internal/agents/project/migrate.go. Layout math: internal/agents/config/layout.go. :::

::: tip Renamed from "Workspace" Projects replace the old Workspace concept (familiar term from Codex/Claude). On first boot after upgrade, every existing workspace is migrated 1:1 into a project with the same folder + defaults, and sessions are re-linked automatically — no data loss. The old workspaces/ directory is kept on disk as a defensive backup. :::

Two kinds: managed vs custom

Kind Where the files live Created by Wick deletes on project delete?
Managed ~/.<app>/agents/projects/<id>/files/ Wick (MkdirAll at create time) — empty folder Yes
Custom path Any absolute path you point at (e.g. D:/code/myproject, ~/scratch) You (must already exist before you create the project) No — wick never owned it, wick never deletes it

The custom-path requirement that the directory must already exist is enforced at create time — typos surface immediately, not at first spawn.

A project can hold zero, one, or many repos. There's no git worktree, no auto-clone, no master-branch model. The agent does the cloning itself via Bash if you ask it to.

The folder is part of the project's identity: there's no multi-folder project. Want a different folder? Create another project, or move the session to one.

Read the full file on GitHub · 234 lines

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.

  1. yesterday First seen · 234 lines · 0 tokens per session scan A 8d20a6e008a2

Subscribe to this mod's changes

projects is an agent published in the GitHub repository yogasw/wick (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,179 tokens. 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.

Related

Other agents, from other repositories

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

Writing Reviewer

Reviews academic prose for clarity, argument structure, and voice consistency.

chrisblattman/claudeblattman · 15 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

platform-engineer

Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit · 88 tokens