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.
curl -O https://raw.githubusercontent.com/chrzanowy/agent-tollbooth/main/.claude/skills/tollbooth/SKILL.mdgit clone --depth 1 https://github.com/chrzanowy/agent-tollboothWrote 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.
[](https://agentmods.dev/skills/chrzanowy/agent-tollbooth/tollbooth)<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/tollbooth"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/tollbooth/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.
<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/tollbooth"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/tollbooth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00152 | $0.01463 |
| Opus 5.5 | $0.00061 | $0.00585 |
| Sonnet 5.5 | $0.00030 | $0.00293 |
| Haiku 4.5 | $0.00015 | $0.00146 |
Grade A, and why
tollbooth 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.
otherwise every example below is a plain HTTP call you can make with curl. How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tollbooth — state that survives your session
tollbooth is a local service (default http://localhost:4402) holding state that
outlives you: memories, page snapshots, a browser, a code runner, and shared
boards. If its MCP tools (memory_store, memory_recall, watch_add,
watch_check, watch_list, render_extract, execute_run, board_open,
board_list, board_post, board_read, board_digest) are available, use them;
otherwise every example below is a plain HTTP call you can make with curl.
Every response includes a receipt (tool, price, latency). On a local instance
prices are $0 — receipts exist so spend is auditable when a hosted tier is used.
memory — facts for your future self
At the start of substantive work in a project, recall before you explore:
curl -s 'localhost:4402/memory?q=<topic>' # full-text search
curl -s 'localhost:4402/memory?key=<exact-key>' # exact key
Store when you learn something durable that the repo itself does not record — a user preference, an environment quirk ("staging DB is readonly on weekends"), a decision and its why, a hard-won debugging conclusion:
curl -s localhost:4402/memory -H 'content-type: application/json' \
-d '{"key":"short-kebab-slug","content":"the fact, with why it matters","tags":["topic"]}'
Do not store what code, git history, or docs already record — memory is for what
would otherwise be lost when the session ends. Overwriting the same key updates it;
DELETE /memory/<key> removes facts that turned out wrong. Use ns to partition
unrelated projects.
watch — "did it change since I last looked?"
Use when the user wants a page tracked over time, or when your task depends on whether something changed between sessions (pricing pages, changelogs, docs, statuses). One agent baselines it once:
curl -s localhost:4402/watch -H 'content-type: application/json' \
-d '{"url":"https://example.com/pricing","note":"why this is watched"}'
Any later session asks — the answer is a unified diff since the last check:
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.
- 2mo ago First seen · 140 lines · 152 tokens per session scan A 796262160d10
tollbooth is a skill published in the GitHub repository chrzanowy/agent-tollbooth (0 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 1,463 once invoked, about $0.0006 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.
tollbooth compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tollboothchrzanowy/agent-tollbooth | Skill | 0 | 2mo ago | MIT | A | 152 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |