fresh

A development-workflow command that saves the current plan and identifies the next task before a fresh conversation starts.

In plain words
What is it for?
Use it to save progress in a .devloop project, record the next action, and resume the plan after restarting the context.
Why use it?
It prevents unfinished work from losing its place when the agent's context needs to be reset.

Skill for Claude CodeCodex

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 skills/zate/cc-plugins/fresh
Any agent
npx skills add Zate/cc-plugins --skill fresh
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 709 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 $0.00012 $0.00709
Opus 5 $0.00006 $0.00354
Sonnet 5 $0.00002 $0.00142
Haiku 4.5 $0.00001 $0.00071

Measured 2d ago against content hash e972d7aea06a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fresh 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 2d ago.

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.

plugins/devloop/skills/fresh/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fresh Start

Save the current devloop plan state for resuming after a context reset. You do the work directly.

Step 1: Read Current Plan

Use the Read tool to read .devloop/plan.md.

If no plan exists, tell user to run /devloop first.

Step 2: Find Current Task

Identify the next pending task (first - [ ] in the plan).

Step 3: Save State

Write to .devloop/next-action.json:

{
  "task": "Task X.Y: Description",
  "phase": "Current Phase Name",
  "notes": "Any context about work in progress",
  "saved_at": "YYYY-MM-DD HH:MM"
}

Step 4: Confirm

Tell user:

State saved to .devloop/next-action.json

Next steps:
1. Run /clear to reset context
2. Run /devloop:run to resume work

Tip: Before doing a full /devloop:fresh + /clear, try pressing Esc+Esc first. This triggers partial summarization which compresses your context without losing state — often enough to keep working without a restart.

Note: The next-action.json file is consumed (deleted) when /devloop:run runs.


Token Efficiency & Fresh Threshold

The default fresh_threshold is 10 tasks. However, token-heavy workloads exhaust session context faster and benefit from a lower threshold.

Recommended thresholds by workload:

Workload Recommended fresh_threshold Why
Sequential tasks (default) 10 One agent at a time, moderate context growth
Swarm (parallel workers) 5-7 Each spawn adds its full context; N parallel spawns = N× context cost
Large token_budget (8000+) 5 Heavy context per task exhausts budget sooner
1M context model 25-50 Much larger budget; fresh restarts are less urgent
Epic phases (run-epic) 10 (default) Phases run inline like /devloop:run; pause at phase boundaries for /clear if context is heavy

When to lower the threshold:

  • Running /devloop:run-swarm with 5+ concurrent workers per batch
  • Using a high tokens.token_budget (>8000) in local.md
  • Experiencing slow responses or context warnings before completing the plan

Read the full file on GitHub · 92 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. 2d ago First seen · 92 lines · 12 tokens per session scan A e972d7aea06a

Subscribe to this mod's changes

fresh is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 709 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens