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.
npx agentmods add agents/zama-ai/sdk/gotchasgit clone --depth 1 https://github.com/zama-ai/sdkWrote 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/agents/zama-ai/sdk/gotchas)<a href="https://agentmods.dev/agents/zama-ai/sdk/gotchas"><img src="https://agentmods.dev/badge/agents/zama-ai/sdk/gotchas.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00659 |
| Opus 5 | $0.00000 | $0.00329 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
gotchas 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 3d 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.
The source is not reproduced here
Licensed BSD-3-Clause-Clear
The repository is licensed BSD-3-Clause-Clear, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 3d ago First seen · 16 lines · 0 tokens per session scan A e38c9cd77832
gotchas is an agent published in the GitHub repository zama-ai/sdk (11 stars, last pushed 6d ago), licensed BSD-3-Clause-Clear. It costs nothing until one of its globs matches a file; then it loads 659 tokens. 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 2026-08-30.
Other agents, from other repositories
letta
Letta (v1.15.x+, early January 2027) is a framework for creating stateful AI agents with "infinite" memory. It manages memory as a tiered system (long-term, short-term) to overcome LLM context window limits by treating the context window as a "cache" for a larger, persistent memory store, now natively supporting the…
mem0
Mem0 (v2.5+, early January 2027) is a specialized memory and personalization layer for AI agents and applications that stores, prioritizes, and retrieves durable user, task, and workflow context over time. Often described as the "long-term memory" of the agentic stack, it enables agents powered by Claude 5.6, GPT-5.6…
phidata
Phidata is a Python-native framework for building AI assistants with memory, knowledge, and tools. As of early January 2027, Phidata has fully transitioned and rebranded into the Agno framework (v3.x). It serves as a primary enterprise bridge for transforming raw LLMs into stateful, autonomous agents, offering native…
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
note-scorer
Batch note quality scorer for the Obsidian vault. Reads notes, applies promote-gate scoring mode, returns structured scores and action recommendations.