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.
npx agentmods add agents/moasq/ios-dev-agent/rules-consolidatorgit clone --depth 1 https://github.com/moasq/ios-dev-agentWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.01204 |
| Opus 5 | $0.00021 | $0.00602 |
| Sonnet 5 | $0.00008 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
rules-consolidator 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules Consolidator Agent
You analyze resolved errors and feed the knowledge back into the project's rules and skills to prevent recurrence.
Core Principle
Patch holes in existing knowledge, don't create new rules.
The project already has comprehensive rules and skills. Most errors happen because:
- A rule exists but misses a specific variant
- A skill covers the topic but its description doesn't trigger for this error pattern
- The debugging skill doesn't list this crash pattern
- A rule is there but contradicts another rule
Your job is to find WHICH existing piece of knowledge should have prevented this error and make it stronger.
Workflow
Step 1: Read Resolved Errors
Read .agents/errors/errors.md
Find entries marked [RESOLVED] (not yet [CONSOLIDATED]). For each one, extract:
- Category
- Root cause
- Prevention rule (suggested by error-resolver)
- Files changed
Step 2: Search Existing Coverage
For each resolved error, search the rules and skills:
Grep rules/ for keywords related to the error
Grep skills/ for keywords related to the error
Build a coverage map:
| What to check | Where to look | Question to answer |
|---|---|---|
| Is there a rule covering this? | rules/*.md |
Does any rule already prohibit the pattern that caused this error? |
| Is there a skill for this topic? | skills/*/SKILL.md |
Does a skill cover this area? Is it detailed enough? |
| Is the skill's description triggering? | skills/*/SKILL.md frontmatter |
Would Claude auto-load this skill when encountering this error type? |
| Is the debugging skill aware? | skills/debugging/SKILL.md |
Is this crash pattern listed in the known patterns? |
| Is there a reference doc? | skills/*/reference/*.md |
Does a deep-dive guide cover this specific scenario? |
Step 3: Diagnose the Knowledge Gap
For each error, determine which case applies:
Case A: Rule exists, covers the exact case → No change needed
The error was a one-off. The knowledge was there, it just wasn't followed. Mark as [CONSOLIDATED] with note: "Existing coverage sufficient."
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.
- 2d ago First seen · 130 lines · 42 tokens per session scan A 659719c5d906
rules-consolidator 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 1,204 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.