agent-harness-fault-injection

agent-harness-fault-injection is a skill for Claude Code from iradoweck/antigravity-awesome-skills. It costs 34 tokens per session (2,494 once invoked), scanned A, a copy of agent-harness-fault-injection, MIT.

A testing skill for deliberately injecting controlled failures into an AI agent workflow. It checks how the workflow behaves when tools, workers, checkpoints, memory, or orchestration services fail.

In plain words
What is it for?
Use it to test retry, resume, timeout, isolation, and partial-failure paths in a local or authorized staging harness.
Why use it?
It provides repeatable evidence about whether state, budgets, safety limits, and recovery behavior remain correct during failures.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the agentic-awesome-skills plugin — 196 skills shipped together

Good fit Use it to test retry, resume, timeout, isolation, and partial-failure paths in a local or authorized staging harness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection
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 iradoweck/antigravity-awesome-skills --skill agent-harness-fault-injection
Clone the repo
git clone --depth 1 https://github.com/iradoweck/antigravity-awesome-skills

Made for: Claude Code.

Or install agentic-awesome-skills, the plugin that ships this one along with the rest of its 196 skills.

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 agent-harness-fault-injection

README.md
[![agentmods](https://agentmods.dev/badge/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection/github.svg)](https://agentmods.dev/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection)
Your own site
<a href="https://agentmods.dev/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection"><img src="https://agentmods.dev/badge/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection/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.

agentmods 80×15 button for agent-harness-fault-injection

Your own site · 80×15
<a href="https://agentmods.dev/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection"><img src="https://agentmods.dev/badge/skills/iradoweck/antigravity-awesome-skills/agent-harness-fault-injection.svg" alt="Reviewed on agentmods" width="80" 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 2,494 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 100% copy Near-identical to another mod 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 $0.02494
Opus 5 $0.00017 $0.01247
Sonnet 5 $0.00007 $0.00499
Haiku 4.5 $0.00003 $0.00249

Measured 8d ago against content hash b64b7afa7bbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-harness-fault-injection 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 8d 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.

Origin

This is a copy

100% identical to agent-harness-fault-injection — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/agentic-awesome-skills-claude/skills/agent-harness-fault-injection/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Harness Fault Injection

Overview

Use a deterministic, non-production fault schedule to test whether an agent workflow preserves state, budgets, safety boundaries, and evidence when a dependency fails. The output is a small fault matrix, an event timeline, and a verdict that distinguishes recovered, contained, unrecoverable, and inconclusive runs.

When to Use This Skill

  • Use when a multi-step agent, state machine, loop, or multi-agent workflow has a new recovery path.
  • Use when sandbox execution, an MCP/tool call, a worker, a checkpoint store, or memory can time out or disappear.
  • Use before claiming retry, resume, deadline, isolation, or partial-failure behavior is production-ready.
  • Use when a regression needs reproducible failure evidence instead of a random chaos run.

Do not use this skill against a production target, real user data, live credentials, or an unbounded external service. Convert those cases to a local simulator or an authorized staging harness first.

Safety and Boundary Preconditions

  1. Freeze the workflow revision, model/prompt configuration, tool schemas, seed, input fixture, timeout, retry budget, deadline, and expected terminal states.
  2. Run in a disposable sandbox with synthetic inputs and stubbed tools. Keep network disabled unless the test explicitly needs a local test server.
  3. Make every injected failure an in-memory or fixture-controlled event. Never delete real data, revoke real credentials, kill an unrelated process, or mutate a live service to create a failure.
  4. Record the test scope and a run identifier before starting. A missing scope, fixture, or recovery contract makes the verdict inconclusive.

Recovery Contract

Write the invariant before injecting a fault. A useful contract names the state that must survive and the side effects that must not repeat:

After recovery, resume from the latest durable checkpoint, preserve the task
identity and safety policy, spend no more than the remaining retry/deadline
budget, and commit each externally visible effect at most once.

Read the full file on GitHub · 251 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. 8d ago First seen · 251 lines · 34 tokens per session scan A b64b7afa7bbc

Subscribe to this mod's changes

agent-harness-fault-injection is a skill published in the GitHub repository iradoweck/antigravity-awesome-skills (30 stars, last pushed 12d ago), licensed MIT. It adds 34 tokens to every session and 2,494 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-harness-fault-injection, differing in 0 lines, and is treated as a copy.