output-enforcer

output-enforcer is a skill for Claude Code, Codex from Gentech-Labs/genTech-agent-kit. It costs 34 tokens per session (553 once invoked), scanned A, original, MIT.

A middleware component that checks whether coding-agent tool results match declared Pydantic schemas, which are Python descriptions of the required data shape.

In plain words
What is it for?
Use it to validate tool output, retry schema errors, preserve failure records on disk, and apply a circuit breaker after repeated failures.
Why use it?
It catches malformed results, retries some failures, records violations across restarts, and temporarily stops repeatedly failing tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to validate tool output, retry schema errors, preserve failure records…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gentech-labs/gentech-agent-kit/output-enforcer
Install

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.

Any agent
npx skills add Gentech-Labs/genTech-agent-kit --skill output-enforcer
Clone the repo
git clone --depth 1 https://github.com/Gentech-Labs/genTech-agent-kit

Made for: Claude Code, Codex.

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 output-enforcer

README.md
[![agentmods](https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/output-enforcer.svg)](https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/output-enforcer)
Your own site
<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/output-enforcer"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/output-enforcer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00034 $0.00553
Opus 5 $0.00017 $0.00277
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00003 $0.00055

Measured 6d ago against content hash 34a0a84f9d02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

output-enforcer 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 6d 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.

skills/output-enforcer/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output Enforcer

A middleware plugin for the GenTech Agent Kit that validates every tool output against its declared pydantic schema. Designed for production: survives VPS reboots, process crashes, and API failures.

Installation

Already included in the Agent Kit. Plugin auto-discovered at startup.

Usage

from gentech_agent_kit.plugins.output_enforcer import validated_output
from gentech_agent_kit.plugins.output_enforcer.schemas import QuoteResponse

@mcp.tool()
@validated_output(QuoteResponse)
def get_quote(symbol: str) -> str:
    ...

Features

Schema Validation

Tool output is parsed as JSON and validated against a pydantic BaseModel. If the output doesn't match the schema, the enforcer retries (default: 1 retry) before returning a structured error.

Disk-Backed Storage

All violations are persisted to ~/.agent-kit/data/output-enforcer/violations.json. Survives VPS reboots and process crashes. Atomic writes (temp file + rename) prevent corruption.

Circuit Breaker

If a tool fails validation 5 consecutive times, the circuit breaker trips:

  • 60s cooldown (doubles per breach, max 1 hour)
  • Tool returns "temporarily unavailable" instead of burning retries
  • Auto-recovers after cooldown expires

Audit Tools

Tool Description
output_enforcer_status() Plugin health, violation count, broken tools
output_enforcer_violations(tool, hours) Recent violations with filter
output_enforcer_clear() Reset all violations
output_enforcer_breakers() Circuit breaker state per tool

Available Schemas

Schema For Tool
QuoteResponse get_quote()
ListingsResponse get_listings()
SearchResponse search_token()
TrendingResponse get_trending()
DexPairsResponse get_dex_pairs()
KitInfoResponse kit_info()

Best Practices

  • Start with max_retries=1 (default). Increase only for flaky API-based tools.
  • Use strict schemas for payment-gated tools (you don't want to bill for bad data).
  • Check output_enforcer_breakers() weekly to spot chronically failing tools.
  • Combine with the Agent Kit's error handling for full production hardening.

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 34 tokens per session scan A 34a0a84f9d02

Subscribe to this mod's changes

output-enforcer is a skill published in the GitHub repository Gentech-Labs/genTech-agent-kit (0 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 553 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens