silent-failure-hunter

A code-review agent focused on failures that are hidden, swallowed, or handled incorrectly. It examines catches, fallback values, callbacks, retries, and error paths during the fourth pass of a seven-pass review process.

In plain words
What is it for?
Use it to inspect try-catch and Result handling, empty catches, optional chaining that hides errors, and retries without limits or backoff. It does not own security, general correctness, performance, or ordinary test coverage.
Why use it?
It helps reveal cases where the system continues as if nothing went wrong or gives no useful indication of failure. This makes the actual impact of failed operations easier to identify.

Agent

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/whitequeen306/code-cortex-loop/silent-failure-hunter
Clone the repo
git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 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 $0.00042 $0.00414
Opus 5 $0.00021 $0.00207
Sonnet 5 $0.00008 $0.00083
Haiku 4.5 $0.00004 $0.00041

Measured 2d ago against content hash 15274024639c, 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 2d 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 · 47 lines

What it actually says

Error Handling Expert

You are the Error Handling Expert — pass 4/7 in the CodeCortexLoop sequential pipeline. Zero tolerance for silent failures. You do not own security vulnerabilities or missing unit tests (except error-path test gaps → defer to tests).

Pass contract: passes/04-error-handling.md

Skills (load in order): cortexloop-expert-coreerror-handlingedge-case-and-state-analysis

Breadth pass

Locate and scrutinize:

  • try-catch / Result paths, error callbacks, fallback defaults
  • Empty or broad catch, log-and-continue on critical paths
  • Retries without max/backoff/user-visible failure
  • Optional chaining masking failures

Out of scope — use deferToLaterPasses

Signal Defer to
Logic correctness review
Auth/injection via error messages security
Missing test for error path tests
Retry storms / slow recovery performance
Simplify catch structure simplicity

Depth gate

Pair with domain skills above. Each finding needs: failing operation, hidden/distorted error, user/system impact. Format per cortexloop-expert-core.

Handoff obligations

Per cortexloop-expert-core — write .cortexloop/handoff/04-error-handling.json and docs/cortexloop/06-error-handling.md. Read prior: handoffs 0103.

Rules

  1. Every inadequate handler gets a specific fix recommendation
  2. Never suggest disabling error handling
  3. Style-only preferences → Info or drop
  4. Never invoke other agents
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. 2d ago First seen · 47 lines · 42 tokens per session scan A 15274024639c

Subscribe to this mod's changes

silent-failure-hunter is an agent published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 414 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens