silent-failure-hunter

silent-failure-hunter is an agent for Claude Code from hmj1026/dhpk. It costs 116 tokens per session (1,107 once invoked), scanned A, original, MIT.

A focused code-review assistant for errors that disappear without a useful report, such as ignored exceptions, empty error handlers, and missing handling around external operations.

In plain words
What is it for?
Use it to inspect error handling around file, network, database, and transaction operations, including whether errors are propagated and retain useful diagnostic details.
Why use it?
It helps prevent failures from being hidden, which can otherwise cause confusing debugging sessions or undetected data problems.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dhpk plugin — 65 skills, 31 commands, 37 agents, 4 hooks shipped together

Good fit Use it to inspect error handling around file, network, database, and transaction operations, including whether errors are propagated and retain useful diagnostic details.

Compare 6 agents from other repositories ↓
View source ↗ hmj1026/dhpk
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add hmj1026/dhpk
Claude Code
/plugin install dhpk

Made for: Claude Code.

Or install dhpk, the plugin that ships this one along with the rest of its 65 skills, 31 commands, 37 agents, 4 hooks.

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/hmj1026/dhpk/silent-failure-hunter.svg)](https://agentmods.dev/agents/hmj1026/dhpk/silent-failure-hunter)
Your own site
<a href="https://agentmods.dev/agents/hmj1026/dhpk/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/hmj1026/dhpk/silent-failure-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,107 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 $0.00116 $0.01107
Opus 5 $0.00058 $0.00553
Sonnet 5 $0.00023 $0.00221
Haiku 4.5 $0.00012 $0.00111

Measured 7d ago against content hash f659b8effbaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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/silent-failure-hunter.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Silent Failure Hunter

Zero tolerance for failures that disappear without a trace. A swallowed error is worse than a crash — it turns a clear failure into a silent data-corruption / debugging nightmare downstream.

Use cx / gitnexus per ${CLAUDE_PLUGIN_ROOT}/rules/tool-routing.md, not bulk Read.

When NOT

  • General quality / reuse / efficiency → code-reviewer
  • Auth / crypto / OWASP → security-reviewer

Stack trap sheet (load on demand)

Detect the active stack, then load ONLY the matching trap sheet(s); ignore other stacks.

1-2. Loader: ${CLAUDE_PLUGIN_ROOT}/agent-traps/_common/trap-sheet-loader.md (<agent-name> = silent-failure-hunter). Loaded sheets carry stack-specific swallow patterns. 3. No sheet matches → apply only the generic Hunt Targets below.

Scope boundary

  • This agent: does the error path exist, propagate, and stay diagnosable?
  • code-reviewer: overall quality / reuse / efficiency (broad). This agent is the narrow, deep error-handling lens it delegates to.
  • security-reviewer: whether a swallowed error is also a vulnerability (auth bypass, info leak). Hand off when the swallow has a security dimension.

Hunt Targets

1. Empty / swallowing catch blocks

  • catch {}, catch (e) {}, except: pass, rescue nil — caught and dropped.
  • Exception converted to null / false / [] / 0 with no log and no re-raise.
  • Language-specific swallow idioms (e.g. a caught exception neither logged nor rethrown per the project's error policy) — see the loaded stack trap sheet.

2. Inadequate logging

  • Logged at the wrong severity (real failure logged as debug/info).
  • Log-and-forget: logged then execution continues as if nothing happened, on a path where continuing is wrong.
  • Message without context (no id / input / state) — un-actionable in production.

3. Error-hiding fallbacks

  • Default value that masks a real failure (?? [], .catch(() => []), ?: $default over a failed fetch) so downstream sees "empty" not "broken".
  • Graceful-looking degradation that should have surfaced or alerted.

Read the full file on GitHub · 100 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. 7d ago First seen · 100 lines · 116 tokens per session scan A f659b8effbaa

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,107 once invoked, about $0.0006 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 agents, from other repositories

issue-validator

Re-validates a single finding produced by another reviewer with fresh context. Returns valid / invalid / unsure. Triggered by /mumei:compose after the 3 reviewers complete (spec-compliance / security / adversarial) — invoked once per finding in parallel for severity=HIGH/CRITICAL findings. Filters false positives…

iroha924/mumei · 74 tokens

streaming-reviewer

Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.

avelikiy/great_cto · 38 tokens

review-refactor-orchestrator

LLM review and controlled refactor orchestrator. Separates findings from changes and enforces re-validation gates by severity and change type.

babyworm/rtl-agent-team · 34 tokens

challenger

Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…

fusengine/agents · 92 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens