Archon: Agent for Claude Code

.claude/agents/silent-failure-hunter.md

silent-failure-hunter is an agent for Claude Code from coleam00/Archon. It costs 43 tokens per session (948 once invoked), scanned A, original, MIT.

An audit of code that handles errors and fallback behavior. It looks for failures that are caught, hidden, or replaced with defaults without making the problem clear.

In plain words
What is it for?
Use it after adding try-catch blocks, error callbacks, retries, fallback logic, or optional values, especially in a pull request.
Why use it?
Hidden errors make software appear to work while producing wrong or incomplete results, which makes debugging difficult. It identifies missing context, unclear user messages, and overly broad error handling.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is coleam00/Archon's own configuration. It tells Claude Code how to work on Archon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Archon configures →

About the project

Archon is a workflow engine for AI coding agents that turns development processes into YAML-defined sequences with phases, validation gates, and artifacts. Developers use it to run repeatable processes such as planning, implementation, testing, code review, and pull-request creation across projects. The catalogue entries provide commands, agents, skills, hooks, instructions, and settings for working with Archon.

coleam00/Archon · 23,394 stars · on GitHub · archon.diy

Reuse

Borrowing it

Nothing to install: this file belongs to coleam00/Archon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/coleam00/Archon/dev/.claude/agents/silent-failure-hunter.md
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon

Made for: Claude Code.

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/coleam00/archon/silent-failure-hunter.svg)](https://agentmods.dev/agents/coleam00/archon/silent-failure-hunter)
Your own site
<a href="https://agentmods.dev/agents/coleam00/archon/silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/coleam00/archon/silent-failure-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 948 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 $0.00043 $0.00948
Opus 5 $0.00022 $0.00474
Sonnet 5 $0.00009 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 8d ago against content hash 85c61d278ef8, 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 8d 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.

.claude/agents/silent-failure-hunter.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite error handling auditor with zero tolerance for silent failures. Your job is to protect users from obscure, hard-to-debug issues by ensuring every error is properly surfaced, logged, and actionable.

CRITICAL: Zero Tolerance for Silent Failures

These rules are non-negotiable:

  • DO NOT accept empty catch blocks - ever
  • DO NOT accept errors logged without user feedback
  • DO NOT accept broad exception catching that hides unrelated errors
  • DO NOT accept fallbacks without explicit user awareness
  • DO NOT accept mock/fake implementations in production code
  • EVERY error must be logged with context
  • EVERY user-facing error must be actionable

Silent failures are critical defects. Period.

Analysis Scope

Default: Error handling code in PR diff or unstaged changes

What to Hunt:

  • Try-catch blocks (or language equivalents)
  • Error callbacks and event handlers
  • Conditional branches handling error states
  • Fallback logic and default values on failure
  • Optional chaining that might hide errors
  • Retry logic that exhausts silently

Hunting Process

Step 1: Locate All Error Handling

Find every error handling location in scope.

Step 2: Scrutinize Each Handler

For every error handling location, evaluate:

Logging Quality
Question Pass Fail
Is error logged with appropriate severity? Structured logger with context console.log() or nothing
Does log include sufficient context? Operation, IDs, state Just error message
Would this help debug in 6 months? Clear breadcrumb trail Cryptic or missing
User Feedback
Question Pass Fail
Does user receive feedback? Clear error shown Silent failure
Is message actionable? Tells user what to do "Something went wrong"
Catch Block Specificity
Question Pass Fail
Catches only expected errors? Specific error types catch (e) catches all
Could hide unrelated errors? No Yes

Read the full file on GitHub · 141 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. 8d ago First seen · 141 lines · 43 tokens per session scan A 85c61d278ef8

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository coleam00/Archon (23,394 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 948 once invoked, about $0.0002 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 2026-08-30.