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 skills/phuonghx/aim-cli/simplify-codenpx skills add phuonghx/aim-cli --skill simplify-codegit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00101 | $0.01007 |
| Opus 5 | $0.00051 | $0.00504 |
| Sonnet 5 | $0.00020 | $0.00201 |
| Haiku 4.5 | $0.00010 | $0.00101 |
Grade A, and why
simplify-code 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify Code
Code costs more to read than to write. Treat every extra layer, branch, and clever trick as a debt that future readers pay interest on. Remove it unless it earns its keep.
The one rule that governs the rest
Simplicity is not a style preference; it is the absence of structure that does not pull its weight. Keep an abstraction only when you can name the concrete benefit it provides right now. "We might need it later" is not a benefit you have today.
What to hunt for
Indirection that adds nothing
| You see | You probably want |
|---|---|
| A class that forwards every call to another object | The inner object, used directly |
| A factory that only ever builds one concrete type | A plain constructor call |
| An interface with exactly one implementer | The concrete class, interface deleted |
| A "strategy" with a single strategy | An ordinary function |
| A base class extended by one subclass | The two folded together |
| An options struct holding two fields | Two positional arguments |
Code nothing reaches
- Imports referenced nowhere
- Branches that can never be true (confirm via tests before deleting)
- Old code left behind in comments — version control already remembers it
- Variables assigned but never read; functions called from nowhere
- Stale
TODOnotes — act on them or file a ticket, then delete - Toggles guarding a feature that already shipped to everyone
Pyramids of nesting
Flatten with guard clauses and pipeline-style collection methods.
# Tangled: four levels before any real work happens
def notify_active(payload):
if payload:
if payload.get("recipients"):
for r in payload["recipients"]:
if r.get("subscribed"):
send(r)
# Flat: bail early, then express the intent in one chain
def notify_active(payload):
recipients = (payload or {}).get("recipients") or []
for r in recipients:
if r.get("subscribed"):
send(r)
Functions that ask for too much
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.
- yesterday First seen · 109 lines · 101 tokens per session scan A 786cb9b5e27c
simplify-code is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,007 once invoked, about $0.0005 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 skills, from other repositories
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).