A way to resume long-running work from a project board that stores durable progress between sessions. It loads the relevant board and continues from its latest recorded context instead of rereading old chat transcripts.

Use it when starting work with an active board or when asked to warm-start, continue from the board, or pick up where previous work stopped.

It reduces catch-up time and preserves progress when work spans multiple sessions or agents.

How chrzanowy/agent-tollbooth configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrzanowy/agent-tollbooth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/chrzanowy/agent-tollbooth/main/.claude/skills/warmstart/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/chrzanowy/agent-tollbooth

Made for: Claude Code.

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/chrzanowy/agent-tollbooth/warmstart/github.svg)](https://agentmods.dev/skills/chrzanowy/agent-tollbooth/warmstart)

Your own site

<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/warmstart"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/warmstart/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/chrzanowy/agent-tollbooth/warmstart"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/warmstart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 574 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00087	$0.00574
Opus 5	$0.00044	$0.00287
Sonnet 5	$0.00017	$0.00115
Haiku 4.5	$0.00009	$0.00057

Measured 9d ago against content hash 5daa7e665654, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

warmstart scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s 'localhost:4402/board?query=repo:<host>/<owner>/<name>'

.claude/skills/warmstart/SKILL.md · 50 lines

What it actually says

resume — warm-start from a board

A previous session (possibly a different model or harness) left its durable context on a board. Your job: load it cheaply, then continue the work — not summarize it back to the user.

Steps

Find the board. If the user named a topic or context, open it directly (board_open or POST /board/open). Otherwise derive the project prefix from the git remote (repo:<host>/<owner>/<name>) and list its contexts — the prefix query is the project's context map:
```
curl -s 'localhost:4402/board?query=repo:<host>/<owner>/<name>'
```
(or board_list). Each row carries topic, description, and latest_seq. If there is exactly one board, use it. If there are several (repo:.../ctx:<slug> workstreams beside the project inbox), show the user a short menu — description + topic per line — and ask which context to resume; do not guess between active workstreams.
Catch up with one read. The default read is the warm start: latest digest + only the entries the digest does not cover:
```
curl -s 'localhost:4402/board/<id>?limit=1000'
```
Treat the digest as ground truth for everything before covers_seq; the uncovered entries are what happened since. Do NOT page through raw history (since_seq=0) unless a specific ambiguity forces you to — that re-spends exactly the tokens the digest saved.
Continue the work. The digest/entries should name a next action — start there. Briefly tell the user what state you resumed from (one or two sentences), then act. If the board is empty or has no next action, say so and ask for direction instead of guessing.
Close the loop. When you reach a milestone or the session winds down, post a checkpoint (see the checkpoint skill): conclusions, decisions with why, and the next action — so the board stays resumable for whoever comes after you.

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.

9d ago First seen · 50 lines · 87 tokens per session scan A 5daa7e665654

Subscribe to this mod's changes

warmstart is a skill published in the GitHub repository chrzanowy/agent-tollbooth (0 stars, last pushed 24d ago), licensed MIT. It adds 87 tokens to every session and 574 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Project management

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens

agent-tollbooth: Skill for Claude Code