Langchain Dependencies
langchain-ai/langchain-skills
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents.
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
Install Failproof AI SDK Integration
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install FailproofAI/failproofai failproofai-sdk --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sdk/python/skill .claude/skills/failproofai-sdk && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .claude/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install FailproofAI/failproofai failproofai-sdk --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/sdk/python/skill .agents/skills/failproofai-sdk && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .agents/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install FailproofAI/failproofai failproofai-sdk --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/sdk/python/skill .cursor/skills/failproofai-sdk && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .cursor/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/FailproofAI/failproofai.git --path sdk/python/skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install FailproofAI/failproofai failproofai-sdk --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/sdk/python/skill .gemini/skills/failproofai-sdk && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .gemini/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install FailproofAI/failproofai failproofai-sdkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .github/skills && cp -r skills-src/sdk/python/skill .github/skills/failproofai-sdk && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .github/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FailproofAI/failproofai --skill failproofai-sdk -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install FailproofAI/failproofai failproofai-sdk --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FailproofAI/failproofai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/sdk/python/skill .opencode/skills/failproofai-sdk && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "failproofai-sdk" agent skill from https://github.com/FailproofAI/failproofai/tree/main/sdk/python/skill into .opencode/skills/failproofai-sdk/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failproofai-sdk", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
failproofai-sdk- GitHub stars
- 5.3k
- Token cost
- ~6k tokens
- SKILL.md length
- 3,261 words
- Files
- 8 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.
- Works in 7 steps: Install it → Plan before you instrument → The contract → …
- Adding observability to a custom agent so its runs appear in Failproof AI
- SKILL.md covers 1. Install it, 2. Plan before you instrument, 3. The contract and 4. Write it, plus 3 more sections
- Calls python, pip and docker; needs FAILPROOFAI_EVALUATOR_TOKEN
What it does
The skill covers two packages that write the same 15 events in one wire format to the same spool directory: failproofai-sdk for Python and @failproofai/sdk for Node, Bun, Deno and Next.js. You call the SDK at points you choose inside your agent, and it appends structured events to local .jsonl files that a separate collector ships onward. Its job ends at the file, so the integration can be verified on a laptop with no server, API key or network.
The API is small, 15 keyword-only event methods, so the work lies in deciding where to call them and recognizing which silences are bugs, since the SDK does not raise when used wrongly. The sections run through planning, code, proof and scoring: a framework adapter (LangChain, LangGraph, CrewAI, LlamaIndex, Pydantic AI, Vercel AI SDK or Mastra) or a hand-built loop, checks that events are written, and an evaluator worker in Python or TypeScript that scores finished sessions on your own infrastructure. A warning says to install failproofai-sdk and never the similarly named agenteye package.
When your agent uses it
- Adding observability to a custom agent so its runs appear in Failproof AI
- Debugging an integration that writes no events
- Writing, deploying or debugging an evaluator worker that scores recorded sessions
- Planning where in an agent loop events should be recorded
Example prompts
- “Add observability to my LangGraph agent so its runs show up in Failproof AI.”
- “My agent shows nothing in Failproof AI. Work out why no events are being written.”
- “Write a Python evaluator worker that runs an LLM judge on our own infrastructure.”
Requirements
- Python with pip, or Node.js 20.9 or newer, Bun or Deno
Workflow steps
7 steps, taken from the step headings in SKILL.md.
- Install it
- Plan before you instrument
- The contract
- Write it
- Verify — watch the files
- Production — the collector has to agree with you
- Score the runs — your own evaluator worker
What it can do on your machine
Read from SKILL.md and the folder at commit 4fb46aa. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pythonpipdockerpipxnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, docker, pipx and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
FAILPROOFAI_EVALUATOR_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Failproof AI SDK Integration loads about 6k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 250 tokens; SKILL.md has 3,261 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 3,261 words (~6,017 tokens).
“Two packages, one pipe: failproofai-sdk (Python, imported as failproofai_sdk) and @failproofai/sdk (TypeScript/JavaScript). They write the same 15 events in the same wire format into the same spool directory. Everything in this file is language-neutral unless it says otherwise, and code…”
- name
- failproofai-sdk
Files
SKILL.md and 7 other files (references) in sdk/python/skill of FailproofAI/failproofai.
- SKILL.md
- agents/openai.yaml
- references/evaluator.md
- references/events.md
- references/frameworks.md
- references/install.md
- references/integration.md
- references/typescript.md
Open the folder on GitHubat commit 4fb46aa
Compare with similar skills
Failproof AI SDK Integration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Failproof AI SDK Integration this skillFailproofAI/failproofai | 5.3k | — | ~6k | Automated safety check: Pass | Custom licence | |
| Langchain Dependencieslangchain-ai/langchain-skills | 1.3k | 1 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Phoenix Integration SnippetsArize-ai/phoenix | 12k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Langgraph Testing Evaluationsoba-labs/langchain-agent-skills | 107 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agentsop Observability Setupagentsope/SkillAlchemy | 457 | — | ~4.4k | Automated safety check: Pass | MIT | |
| Logfire Instrumentationpydantic/skills | 140 | — | ~6.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Phoenix Integration Snippets
Arize-ai/phoenix
Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI.
Langgraph Testing Evaluation
soba-labs/langchain-agent-skills
A skill your agent uses when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory…
Agentsop Observability Setup
agentsope/SkillAlchemy
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover.
- Official
Logfire Instrumentation
pydantic/skills
Add Pydantic Logfire observability to application code — traces, logs, metrics, and AI/agent spans.
Add Example Agent
GetBindu/Bindu
Add a new self-contained example agent under examples/. An agent skill from GetBindu/Bindu.
Related
Categories
Questions about Failproof AI SDK Integration
What does Failproof AI SDK Integration do?
Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs. js.jsonl files that a separate collector ships onward.
When should I use Failproof AI SDK Integration?
Failproof AI SDK Integration fits situations like: adding observability to a custom agent so its runs appear in Failproof AI; debugging an integration that writes no events; writing, deploying or debugging an evaluator worker that scores recorded sessions; planning where in an agent loop events should be recorded.
How do I install Failproof AI SDK Integration in Claude Code?
Run `npx skills add FailproofAI/failproofai --skill failproofai-sdk -a claude-code`. Or copy the skill folder (sdk/python/skill in FailproofAI/failproofai) into .claude/skills/failproofai-sdk in your project. Claude Code loads it when a task matches its description.
How do I install Failproof AI SDK Integration in Codex?
Run `npx skills add FailproofAI/failproofai --skill failproofai-sdk -a codex`. Or copy the skill folder (sdk/python/skill in FailproofAI/failproofai) into .agents/skills/failproofai-sdk in your project. Codex loads it when a task matches its description.
Can I use Failproof AI SDK Integration in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FailproofAI/failproofai --skill failproofai-sdk -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/failproofai-sdk, .gemini/skills/failproofai-sdk, .github/skills/failproofai-sdk and .opencode/skills/failproofai-sdk in your project.
What does Failproof AI SDK Integration need to run?
Going by SKILL.md and its folder, Failproof AI SDK Integration needs the command-line tools its instructions call (python, pip, docker, pipx and npm) and credentials named FAILPROOFAI_EVALUATOR_TOKEN. Our summary lists: Python with pip, or Node.js 20.9 or newer, Bun or Deno.
Does Failproof AI SDK Integration access the network?
SKILL.md contains no URLs. Its commands use pip, docker and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Failproof AI SDK Integration safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Failproof AI SDK Integration use?
Failproof AI SDK Integration has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Failproof AI SDK Integration use?
About 6k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 23k tokens, read only when the agent opens those files.
What are the alternatives to Failproof AI SDK Integration?
Skills that share tags, products or a category with Failproof AI SDK Integration: Langchain Dependencies (langchain-ai/langchain-skills, 1.3k stars), Phoenix Integration Snippets (Arize-ai/phoenix, 12k stars), Langgraph Testing Evaluation (soba-labs/langchain-agent-skills, 107 stars) and Agentsop Observability Setup (agentsope/SkillAlchemy, 457 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Failproof AI SDK Integration?
FailproofAI (a GitHub organization) maintains it in FailproofAI/failproofai, which has 5,250 GitHub stars. The repository was last updated on October 5, 2026.
Source: FailproofAI/failproofai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.