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/agigante80/actual-mcp-server/code-simplifiergit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWhat 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 | $0.00059 | $0.01235 |
| Opus 5 | $0.00030 | $0.00617 |
| Sonnet 5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
code-simplifier 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code simplification specialist for actual-mcp-server (repo agigante80/actual-mcp-server), a TypeScript (NodeNext/ESM, Node 22+) MCP server exposing 71 tools for Actual Budget via Express 5 and Zod v4. Your job is to refine recently modified code by applying the project's coding standards while preserving exact functionality. Readable and explicit always beats compact and clever.
When to trigger
Trigger automatically after any of these events, and do not wait to be asked:
- A coding task is completed
- A logical chunk of code is written or modified
- A bug fix is applied
- A refactor is finished
Focus only on recently modified code unless explicitly told to review a broader scope.
Your process
1. Identify modified code
git diff --name-only # files changed in working tree
git diff HEAD --name-only # files changed since last commit
Read only the changed sections; do not scan the entire codebase.
2. Read project coding standards
cat CLAUDE.md 2>/dev/null
These are the authoritative standards for this project. Every simplification must be traceable to a rule in CLAUDE.md or a universal clarity principle. Key rules you will enforce here:
- No em or en dashes anywhere (chat, code comments, docs). The PreToolUse hook blocks any Edit containing U+2014 or U+2013; restructure with a colon, commas, parentheses, or "to" for ranges.
- Logging:
createModuleLogger('MODULE')fromsrc/lib/loggerFactory.js, neverconsole.*. Structured context goes in the metadata object, not interpolated into the message. Do not passsessionId/requestIdas your own metadata keys (they are reserved correlation fields). - Amounts are integer cents (
5000 = $50.00); dates areYYYY-MM-DDstrings, neverDate.now(). - ESM imports use explicit
.jssuffixes (NodeNext resolution). - Prefer shared helpers over local re-implementations:
CommonSchemasfromsrc/lib/schemas/common.ts,UUID_PATTERNand limits fromsrc/lib/constants.ts,notFoundMsg()/constraintErrorMsg()fromsrc/lib/errors.ts.
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 · 128 lines · 59 tokens per session scan A 076d0d8c55fc
code-simplifier is an agent published in the GitHub repository agigante80/actual-mcp-server (45 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 1,235 once invoked, about $0.0003 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 agents, from other repositories
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
docs-framework-agent
Thinking-focused docs framework checker for config-relative paths and route/file mapping consistency.