agentmods.dev

agent-tollbooth: Skill for Claude Code

.claude/skills/checkpoint/SKILL.md

checkpoint is a skill for Claude Code from chrzanowy/agent-tollbooth. It costs 62 tokens per session (606 once invoked), scanned A, original, MIT.

A session checkpoint that saves important working context to a shared project board for later continuation.

In plain words
What is it for?
Use it when handing work off, pausing a long task, or saving progress before a risky change. It records the current decisions, status, and details needed to continue.
Why use it?
It prevents another session or agent from having to reconstruct the work from the entire conversation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is chrzanowy/agent-tollbooth's own configuration. It tells Claude Code how to work on agent-tollbooth itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-tollbooth configures →

not rated 0repo 2mo ago A scan 62 tokens original MIT
View source ↗ chrzanowy/agent-tollbooth
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/checkpoint/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.

agentmods badge for checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/checkpoint/github.svg)](https://agentmods.dev/skills/chrzanowy/agent-tollbooth/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/checkpoint"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/checkpoint/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.

agentmods 80×15 button for checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/checkpoint"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 606 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00606
Opus 5.5 $0.00025 $0.00242
Sonnet 5.5 $0.00012 $0.00121
Haiku 4.5 $0.00006 $0.00061

Measured 2mo ago against content hash 6b120075eb43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

checkpoint 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 2mo 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/open -H 'content-type: application/json' \
.claude/skills/checkpoint/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

checkpoint — save durable context to the board, on demand

Post ONE entry to the shared tollbooth board capturing what a future session (or a different agent) must know to continue this work without re-reading the transcript. This is invoked deliberately — do not checkpoint on your own schedule; narration belongs in the transcript, which is captured for free.

Steps

  1. Find the board. Derive the topic deterministically from the work: repo:<host>/<owner>/<name> is the project inbox; a distinct workstream within the project gets its own board at repo:<host>/<owner>/<name>/ctx:<slug>. Checkpoint to the workstream board when this session's work belongs to one; default to the inbox. Open it (get-or-create), passing a one-line description when the board might be new — it is what future warmstart menus display:

    curl -s localhost:4402/board/open -H 'content-type: application/json' \
  -d '{"topic":"repo:github.com/owner/name/ctx:auth-refactor","description":"auth refactor workstream"}'

    Or the MCP tool board_open if available.

  2. Read before writing. GET /board/<id> (or board_read) — see what the latest digest and recent entries already cover. Never repeat what is already on the board.

  3. Post one entry (board_post), 5–15 lines, containing ONLY:

    • decisions made this session, each with its one-line why
    • dead ends ruled out (so nobody re-explores them)
    • constraints or facts discovered that no file records
    • the exact next action, concrete enough to start cold
    • unresolved questions blocking that action, if any

    Set author honestly: {"name":"<role>","model":"<your model>","harness":"<your harness>"}.

What NOT to include

Progress narration ("then I ran the tests"), anything the repo or git history records, code that exists in files, praise or hedging. Every line must be something a cold-started agent would otherwise have to rediscover at token cost.

Cost discipline

Read the full file on GitHub · 55 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. 2mo ago First seen · 55 lines · 62 tokens per session scan A 6b120075eb43

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository chrzanowy/agent-tollbooth (0 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 606 once invoked, about $0.0002 per session on Opus 5.5. 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.

Memory and context
Related

checkpoint compared with skills from other repositories

checkpoint next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
checkpointchrzanowy/agent-tollboothSkill02mo agoMITA62Claude Code
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex