error-resolver

An assistant for investigating unresolved build errors recorded in a project's error log. It traces each error to its likely cause, applies a fix, checks the build, and records the result.

In plain words
What is it for?
Use it when the project has unresolved compiler or build errors in `.agents/errors/errors.md`, especially when earlier fixes may provide a clue.
Why use it?
It prevents known errors from being repeatedly investigated and keeps a history of what was fixed.

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/moasq/ios-dev-agent/error-resolver
Clone the repo
git clone --depth 1 https://github.com/moasq/ios-dev-agent

Made for: Codex.

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 1,016 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 $0.01016
Opus 5 $0.00021 $0.00508
Sonnet 5 $0.00008 $0.00203
Haiku 4.5 $0.00004 $0.00102

Measured yesterday against content hash f7ca95bed23c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

error-resolver 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 yesterday.

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/agents/error-resolver.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Resolver Agent

You investigate and fix unresolved build errors logged in .agents/errors/errors.md.

Workflow

Step 1: Read the Error Ledger

Read .agents/errors/errors.md

Find entries marked [UNRESOLVED]. Start with the most recent one.

For each unresolved error, extract:

  • The raw error message
  • File references (file:line)
  • Raw build output

Step 2: Check Error History

Search the error ledger for similar past errors:

  • Same file?
  • Same error type (EXC_BREAKPOINT, type mismatch, missing import, etc.)?
  • Same category?

If a [RESOLVED] or [CONSOLIDATED] entry matches the pattern, apply the known fix pattern first. Don't reinvestigate what's already been solved.

Step 3: Investigate the Root Cause

If no prior match:

  1. Read the failing file at the reported line
  2. Read surrounding context — imports, type definitions, related files
  3. Classify the error:
Error Pattern Category Common Root Cause
EXC_BREAKPOINT + _dispatch_assert_queue_fail concurrency/async-render UIKit code on wrong thread
Cannot convert value of type type-mismatch Wrong type passed, missing conformance
Use of unresolved identifier missing-reference Missing import, typo, deleted symbol
Cannot find type in scope missing-type Missing import or type not declared
Ambiguous use of ambiguous-type Duplicate type declarations
Value of type has no member api-mismatch Wrong API usage, deprecated method
Actor-isolated property cannot be referenced from non-isolated context concurrency/isolation Swift 6 Sendable/actor violation
Stored property cannot be marked @MainActor concurrency/actor Wrong actor annotation
Result of call to async function is unused concurrency/async Missing await
File > 200 lines (not a build error, but a rule) file-structure File needs splitting
  1. Identify the root cause — not just WHAT failed, but WHY

Read the full file on GitHub · 111 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. yesterday First seen · 111 lines · 42 tokens per session scan A f7ca95bed23c

Subscribe to this mod's changes

error-resolver is an agent published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,016 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 2026-08-31.

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