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 skills add tomzx/agents --skill audit-reliabilitygit clone --depth 1 https://github.com/tomzx/agentsWrote 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/skills/tomzx/agents/audit-reliability)<a href="https://agentmods.dev/skills/tomzx/agents/audit-reliability"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-reliability/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.
<a href="https://agentmods.dev/skills/tomzx/agents/audit-reliability"><img src="https://agentmods.dev/badge/skills/tomzx/agents/audit-reliability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00139 | $0.02341 |
| Opus 5.5 | $0.00056 | $0.00936 |
| Sonnet 5.5 | $0.00028 | $0.00468 |
| Haiku 4.5 | $0.00014 | $0.00234 |
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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Reliability Audit (ISO/IEC 25010)
Audits the codebase for reliability: how the system behaves when components fail, and how it recovers. It finds statically detectable design weaknesses that cause outages and data loss.
This is the Reliability characteristic of the ISO/IEC 25010 quality model.
Distinct from observe-production (is it failing right now?) and audit-observability (is failure instrumented?), this asks: is the system designed to tolerate and recover from failure?
Prerequisites
- Working directory is the root of the repository
- Read
.sdlc/context/architecture.mdif present (for external dependencies and stateful components)
What This Checks
| Sub-characteristic | What it means | Signals scanned |
|---|---|---|
| Maturity | frequency of failure from foreseeable causes | known fragile patterns (bare except, swallowed errors); flaky external calls |
| Availability | operational continuity | single points of failure; stateful singletons assumed unique; missing health/readiness endpoints; missing graceful shutdown |
| Fault tolerance | keeps operating despite hardware/software faults | external calls without timeout; missing retry/backoff; missing circuit breaker on shared dependencies; cascading-failure risks |
| Recoverability | can restore lost data and re-establish the desired state | non-idempotent writes; multi-step writes without transaction boundaries; missing rollback; background jobs without at-least-once/at-most-once clarity; state without persistence |
Steps
1. Exception handling (maturity)
Bare/over-broad exception handlers that swallow errors:
rg -n -A2 "except\s*:|except\s+(Exception|BaseException)\s*:" -g '*.py' . | rg "pass|continue|\.\.\.|return None|return \[\]"
rg -n "catch\s*\(\s*\)\s*\{|catch\s*\{" -g '*.{ts,js,java}' .
Logged-but-swallowed errors (caught, logged, then treated as success):
rg -n -B1 -A3 "except" -g '*.py' . | rg "logger.*\.(info|debug)|console\.(log|debug)"
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.
- 22d ago Changed · +8 lines bfa533320425
- 23d ago Changed · +4 lines ec115e576bf5
- 24d ago Changed 9e7b1801d8d1
- 2mo ago First seen · 187 lines · 139 tokens per session scan A 585ed3190a4c
audit-reliability is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 2,341 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.