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 skills add kivo360/OmoiOS --skill refactor-plannergit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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.
[](https://agentmods.dev/skills/kivo360/omoios/refactor-planner)<a href="https://agentmods.dev/skills/kivo360/omoios/refactor-planner"><img src="https://agentmods.dev/badge/skills/kivo360/omoios/refactor-planner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.01428 |
| Opus 5 | $0.00007 | $0.00714 |
| Sonnet 5 | $0.00003 | $0.00286 |
| Haiku 4.5 | $0.00001 | $0.00143 |
Grade A, and why
refactor-planner 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 7d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Planner
Plan safe, incremental refactoring with proper impact analysis.
Refactoring Workflow
1. Analyze → 2. Plan → 3. Test → 4. Execute → 5. Verify
1. Analyze Current State
- Understand existing code structure
- Map dependencies (what uses this code)
- Identify coupling and cohesion issues
- Document current behavior with tests
2. Plan the Refactoring
- Define target state clearly
- Break into small, reversible steps
- Identify risk points
- Plan rollback strategy
3. Test Coverage First
- Ensure existing tests pass
- Add tests for uncovered behavior
- Create integration tests for dependencies
- Never refactor without tests
4. Execute Incrementally
- One logical change per commit
- Run tests after each step
- Keep the system working throughout
- Commit frequently
5. Verify Results
- All tests still pass
- No new warnings/errors
- Performance unchanged (or improved)
- Dependencies still work
Refactoring Patterns
Extract Function
When: Code block is reused or too complex
# Before
def process_order(order):
# Calculate total
total = 0
for item in order.items:
price = item.price * item.quantity
if item.discount:
price *= (1 - item.discount)
total += price
# ... more code
# After
def calculate_item_price(item) -> float:
"""Calculate price for single item with discount."""
price = item.price * item.quantity
if item.discount:
price *= (1 - item.discount)
return price
def calculate_order_total(order) -> float:
"""Calculate total order price."""
return sum(calculate_item_price(item) for item in order.items)
def process_order(order):
total = calculate_order_total(order)
# ... more code
Extract Class
When: A class has too many responsibilities
# Before: User class doing too much
class User:
def authenticate(self, password): ...
def send_email(self, subject, body): ...
def generate_report(self): ...
# After: Split by responsibility
class User:
def __init__(self):
self.auth = UserAuthenticator(self)
self.notifier = UserNotifier(self)
self.reporter = UserReporter(self)
class UserAuthenticator:
def authenticate(self, password): ...
class UserNotifier:
def send_email(self, subject, body): ...
class UserReporter:
def generate_report(self): ...
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.
- 7d ago First seen · 276 lines · 14 tokens per session scan A f41ded2725ef
refactor-planner is a skill published in the GitHub repository kivo360/OmoiOS (76 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,428 once invoked, about $0.0001 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.
Other skills, from other repositories
self-awareness
Use when the user asks about Archie itself — what Archie is, how it works, what it can or cannot do, what agents or domains exist, how plugins work, how requests get handled, why something behaves a certain way, what integrations are available, or whether Archie can change itself. Triggers on phrases like "what can…
writing-plugins
Read this before authoring or substantially changing a plugin, agent, or skill for Archie. It's the conceptual playbook for building plugins that fit Archie's multi-agent, single-orchestrator model — what a plugin must respect, why every plugin usually needs an orchestrator-facing skill, and how to think about agents…
triggers
Set up, list, or manage triggers — persistent "do Y when X happens" rules. Use when someone asks Archie to do something on a schedule ("every weekday at 9am…", "every morning post…", "remind the channel weekly…"), to react to new messages in a channel ("whenever someone posts X in.
thread-conduct
Use before posting anywhere outside this task's own thread, or when deciding how much to post inside it. Covers keeping one task in one thread, what to do with a finding that belongs to another team, when a cross-channel post is allowed and how small it must be, how much traffic a thread should carry, and how to…
trigger-task
Use when this task was started by a trigger and you have been given a trigger directory — the one place that survives from one fire of that trigger to the next. Covers reading what an earlier fire left before you start work, what is worth leaving behind so a later fire continues instead of repeating, keeping the…
engineering
Engineering task workflow. Use when the task involves code investigation, code changes, bug fixes, feature implementation, or any software engineering work. Provides the engineering task lifecycle, edit mode workflow, and decision framework for coordinating engineering agents.