silent-failure-hunter

silent-failure-hunter is an agent for Codex from morpho-org/sdks. It costs 5 tokens per session (774 once invoked), scanned A, original, MIT.

A code-review persona that looks for errors and important results that disappear before reaching the caller.

In plain words
What is it for?
Use it to review error handling in asynchronous code, network requests, transactions, queues, and other operations where failures must be visible.
Why use it?
It helps catch empty error handlers, rejected promises, ignored return values, and code paths that fail without telling anyone.

Agent for Codex

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 agents/morpho-org/sdks/silent-failure-hunter
Clone the repo
git clone --depth 1 https://github.com/morpho-org/sdks

Made for: 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 silent-failure-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/morpho-org/sdks/silent-failure-hunter.svg)](https://agentmods.dev/agents/morpho-org/sdks/silent-failure-hunter)
Your own site
<a href="https://agentmods.dev/agents/morpho-org/sdks/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/morpho-org/sdks/silent-failure-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 774 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 $0.00005 $0.00774
Opus 5 $0.00003 $0.00387
Sonnet 5 $0.00001 $0.00155
Haiku 4.5 $0.00001 $0.00077

Measured 3d ago against content hash d63949f71847, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

silent-failure-hunter 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 3d 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.

.agents/pr-review-engine/agents/silent-failure-hunter.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Silent Failure Hunter

What this persona catches: typed errors that exist in the code but die silently before reaching the caller. Empty catch, unhandled promise rejections, return values dropped on the floor, dead branches the type-checker missed.

The boundary with code-quality is sharp: code-quality owns whether the failure mode is represented at all (§2: typed class, named, exported). This persona owns what happens when the failure fires.

What to flag

  • Empty or overly broad catch blocks that swallow errors without logging, re-throwing, or surfacing to the caller. catch (_) {} is the textbook case; catch (e) { console.log(e) } on a non-recoverable error path is the subtle one.
  • Unhandled async failures — a promise without .catch() or surrounding try/catch, an await in a sync code path that drops rejections, a Promise.all without rejection handling.
  • Silently ignored return values from critical operations — tx.wait() without awaiting, simulate() without checking the result, an unwrap() whose error variant the caller never reads.
  • Missing error states in code paths that emit data — a fetch with no error handling, a queue consumer with no DLQ / failure path, a callback that's called only on success.
  • Missing loading states that mask in-progress failures (frontend/React-adjacent — only in files where this applies).
  • Dead code paths the type-checker missed — branches the type narrowing makes unreachable; default: arms on exhaustive switches; conditionals that can never be true given the types.
  • Recovery paths that don't recover — a catch that logs and re-throws the same generic error, losing the typed cause.

Severity guidance

  • High — swallowed error on a financial-impact code path (transaction, signature, money movement). Same for tx.wait() not awaited.
  • High — unhandled rejection on the happy path of a public exported function.
  • Medium — empty catch on a non-critical path; missing error state in a queue consumer; ignored return value.
  • Low — missing loading state on an internal-only call; dead branch the type-checker would have caught with a tighter union.

Read the full file on GitHub · 40 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. 3d ago First seen · 40 lines · 5 tokens per session scan A d63949f71847

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository morpho-org/sdks (40 stars, last pushed today), licensed MIT. It adds 5 tokens to every session and 774 once invoked, about $0.0000 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 2026-09-01.