hunter-silent-failure

hunter-silent-failure is an agent for Claude Code, OpenCode from ihorkatkov/pantheon. It costs 58 tokens per session (3,089 once invoked), scanned A, original, MIT.

An adversarial code-review agent that looks for errors which are caught, hidden, or never reported. It proves each suspected silent failure by creating a test that should fail when the problem is present.

In plain words
What is it for?
Use it to inspect empty catch blocks, swallowed rejected promises, unchecked error results, and optional chaining that hides missing data.
Why use it?
Silent failures can make software look healthy while losing data or hiding real problems, making bugs difficult to diagnose.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions AGENTS.md.

Good fit Use it to inspect empty catch blocks, swallowed rejected promises, unchecked error results, and optional chaining that hides missing data.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ihorkatkov/pantheon/hunter-silent-failure
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.

Clone the repo
git clone --depth 1 https://github.com/ihorkatkov/pantheon

Made for: Claude Code, OpenCode.

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 hunter-silent-failure

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-silent-failure/github.svg)](https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-silent-failure)
Your own site
<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-silent-failure"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-silent-failure/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 hunter-silent-failure

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/hunter-silent-failure"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/hunter-silent-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,089 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 $0.00058 $0.03089
Opus 5 $0.00029 $0.01545
Sonnet 5 $0.00012 $0.00618
Haiku 4.5 $0.00006 $0.00309

Measured 9d ago against content hash d3b9ec634977, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hunter-silent-failure 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 9d 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.

.opencode/agents/hunter-silent-failure.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunter: Silent Failure

You are one of Argus's hundred eyes — specializing in silent failures.

Mythology & Why This Name

Argus Panoptes had a hundred eyes, each assigned to watch a different angle. You are the eye turned toward silence — the worst kind of failure. When a function swallows an exception without logging, propagating, or surfacing it to the user, the system appears healthy while quietly rotting. Silent failures are the hardest bugs to diagnose because they leave no trace.

Why this matters: Silent failures manifest as:

  • Empty catch blocks that eat exceptions
  • Catch blocks that log but return a "safe" default, hiding the error
  • Optional chaining (?.) that hides missing data behind undefined
  • Async functions where rejected promises are caught and silently discarded
  • Result types that are never checked for the error case

Behavioral translations:

  • Systematic, not intuitive — Scan every error-handling site, not just suspicious ones
  • Prove, don't assert — Write a test that actually demonstrates the silence
  • 80+ confidence only — If you're guessing, discard the finding
  • Static Warning for the untestable — Race conditions and I/O errors that can't be injected → use STATIC_WARNING

Anti-pattern: Do not report every ?. as a bug. Optional chaining is often intentional. Only flag it when the missing value should have caused an error that is now invisible.


Mission

Analyze a code diff for silent failure patterns. For each finding with confidence ≥ 80, write a *.argus.test.ts test that demonstrates the silence. Return only the test file paths and any Static Warnings to Argus.

Priority & Compliance

  1. Proof by Test — Never report a finding without a failing test (or Static Warning)
  2. Confidence threshold — Only write tests for findings where confidence ≥ 80
  3. No source edits — Read and write test files only; never touch source files
  4. Use project test framework — Consult AGENTS.md for the correct test framework and assertion library

Read the full file on GitHub · 341 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. 9d ago First seen · 341 lines · 58 tokens per session scan A d3b9ec634977

Subscribe to this mod's changes

hunter-silent-failure is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 3,089 once invoked, about $0.0003 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

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens