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/toolbox/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/toolbox)<a href="https://agentmods.dev/skills/chrzanowy/agent-tollbooth/toolbox"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/toolbox/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/toolbox"><img src="https://agentmods.dev/badge/skills/chrzanowy/agent-tollbooth/toolbox.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 | $0.00079 | $0.00494 |
| Opus 5.5 | $0.00032 | $0.00198 |
| Sonnet 5.5 | $0.00016 | $0.00099 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade B, and why
toolbox scanned grade B with 2 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s localhost:4402/memory -H 'content-type: application/json' -d '{ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s 'localhost:4402/memory?q=<problem words>&ns=toolbox' What it actually says
toolbox — did we already find a tool for this?
A shared, machine-global memory namespace answering one question: has any session, in any repo, already found a tool for this problem? Global on purpose — problems recur across projects; boards stay per-project, the toolbox does not.
Habit 1: recall before you build
Before installing, writing, or hand-rolling a solution, search by the problem, not the tool name (a future searcher knows their problem, not your answer):
curl -s 'localhost:4402/memory?q=<problem words>&ns=toolbox'
(or MCP memory_recall with ns: "toolbox"). On a hit, use the stored
invocation and respect its caveats. On a miss, solve it your way — then see
habit 2.
Habit 2: store only what you watched work
Store when a tool has demonstrably succeeded — never when you merely
found it. One plausible-but-untested reference poisons trust in the whole
toolbox. Overwrite the same key when a better tool supersedes it; forget
entries that turn out broken.
curl -s localhost:4402/memory -H 'content-type: application/json' -d '{
"ns": "toolbox",
"key": "<problem-slug>",
"tags": ["tool", "<domain>"],
"content": "problem: <one line, phrased as a searcher would>\ntool: <name + where it comes from>\ninvocation: <the exact command/call that worked>\nverified: <date> — <what you actually observed>\ncaveats: <sharp edges, limits, gotchas>"
}'
Key by problem (publish-mcp-server-registry), not by tool
(mcp-publisher) — the problem is what recurs.
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 · 45 lines · 79 tokens per session scan B cbb814ea3bf5
toolbox is a skill published in the GitHub repository chrzanowy/agent-tollbooth (0 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 494 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
toolbox compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| toolboxchrzanowy/agent-tollbooth | Skill | 0 | 2mo ago | MIT | B | 79 | 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 |