audit-reliability

audit-reliability is a skill for Claude Code, Codex from JHostalek/dotclaude. It costs 92 tokens per session (3,430 once invoked), scanned A, original, CC0-1.0.

A workflow for reviewing and fixing how software behaves during failures, overload, dependency outages, and restarts. It examines concerns such as time limits, retries, duplicate requests, recovery, failover, and reconciling incomplete work.

In plain words
What is it for?
Use it to audit resilience in applications and services, including startup and shutdown behavior, third-party failures, network problems, crashes, slowdowns, overload, configuration mistakes, and deployment issues.
Why use it?
It helps reveal cases where a service may lose data, repeat an action, become unavailable, or recover incorrectly when something goes wrong. The review considers the full path through clients, services, queues, storage, and outside systems.

Skill for Claude CodeCodex

Part of the jhostalek-skills plugin — 32 skills, 12 agents shipped together

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.

agentmods
npx agentmods add skills/jhostalek/dotclaude/audit-reliability
Any agent
npx skills add JHostalek/dotclaude --skill audit-reliability
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Made for: Claude Code, Codex.

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

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 audit-reliability

README.md
[![agentmods](https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-reliability.svg)](https://agentmods.dev/skills/jhostalek/dotclaude/audit-reliability)
Your own site
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-reliability"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-reliability.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00092 $0.03430
Opus 5 $0.00046 $0.01715
Sonnet 5 $0.00018 $0.00686
Haiku 4.5 $0.00009 $0.00343

Measured 5d ago against content hash 47cb944981e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-reliability 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 5d 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/audit-reliability/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"

Run as the reliability dimension. Determine whether the system continues to meet its essential correctness, availability, durability, recovery, and operability contracts through faults, overload, change, and lifecycle transitions. Reliability is end-to-end behavior; do not reduce it to retries, health checks, redundancy, or a resilience library.

Work top-down

  1. Reconstruct intended service behavior from product flows, contracts, schemas, configuration, infrastructure, telemetry, tests, runbooks, and deployment artifacts. Identify essential and degradable capabilities, state and durability guarantees, dependency and ownership boundaries, lifecycle states, workload envelope, recovery objectives, and consequences of delay, duplication, loss, stale results, or unavailability.
  2. Build the failure model. Map synchronous and asynchronous paths across clients, processes, services, queues, storage, caches, third parties, regions, devices, and operators. Include crash, hang, slowdown, partition, corruption, overload, quota, clock, configuration, deployment, and human-operation failures; correlated faults; and dependencies shared by apparent redundancy.
  3. Derive invariants for normal, degraded, recovering, and transitional states. Trace high-consequence scenarios end to end, including faults during mitigation or recovery. Inspect architecture-wide compositions first: individually reasonable timeouts, retries, queues, caches, replicas, autoscaling, and failover can create cascades, duplication, oscillation, or permanent divergence.
  4. Apply the baseline across every applicable component and boundary. Derive extra scenarios from the exact domain, topology, operating model, and history. Verify controls in representative conditions and in the exact call paths they protect.

Do not infer reliability from a framework default, managed service, retry/circuit-breaker helper, queue, transaction, replica, health check, autoscaler, naming convention, common pattern, test presence, or successful happy path. Verify exact versions, configuration, time budgets, state effects, ownership, deployment boundaries, correlated dependencies, and recovery behavior.

Read the full file on GitHub · 164 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. 5d ago First seen · 164 lines · 92 tokens per session scan A 47cb944981e5

Subscribe to this mod's changes

audit-reliability is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 92 tokens to every session and 3,430 once invoked, about $0.0005 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.