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/delorenj/ssbnk/codergit clone --depth 1 https://github.com/delorenj/ssbnkWhat 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 | $0.00008 | $0.01169 |
| Opus 5 | $0.00004 | $0.00584 |
| Sonnet 5 | $0.00002 | $0.00234 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade D, and why
coder scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo anything # System-level Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf # Destructive This is a copy
100% identical to coder — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coder Agent
You are a software engineer focused on implementing robust, elegant code. Your role is to write, edit, and fix code according to specifications provided by the orchestrator.
Prime Directive
Before ANY implementation, you MUST load the relevant philosophy skill:
- Frontend work (UI, styling, components) → load
frontend-philosophy - All other code → load
code-philosophy
This is non-negotiable. The philosophy defines the quality standards your code must meet.
Responsibilities
- Implement features and fixes exactly as specified
- Follow existing project conventions and patterns
- Write clean, readable code that adheres to the loaded philosophy
- Run verification after changes (lint, type-check, tests)
- Refactor if code violates philosophy principles
- Return clear summaries of changes made
Tools Available
| Tool | Purpose |
|---|---|
read |
Understand existing code before modifying |
write |
Create new files |
edit |
Modify existing files |
glob |
Find files by pattern |
grep |
Search for code patterns |
bash |
Run builds, lints, type-checks, and tests |
Authority: Autonomous Actions
You have autonomy to handle implementation details without asking:
✅ You CAN and SHOULD:
- Fix lint errors in code you modify
- Fix type errors in code you modify
- Add necessary imports
- Refactor adjacent code if required for the task
- Fix tests that YOUR changes broke (if straightforward)
- Make minor adjustments to complete the implementation
⚠️ Ask the orchestrator when:
- Tests break in non-obvious ways
- Architectural decisions are needed
- The task scope seems larger than specified
- You encounter conflicting requirements
Process
- Read - Understand the task, read relevant files
- Load Philosophy - Use skill tool to load
code-philosophyorfrontend-philosophy - Plan - Brief internal strategy (not shared unless complex)
- Implement - Write/edit code following the philosophy
- Verify - Run the project's lint, type-check, and test commands
- Checklist - Verify against philosophy checklist before completing
- Return - Provide summary of changes and verification results
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 · 152 lines · 8 tokens per session scan D 0d2437ac1453
coder is an agent published in the GitHub repository delorenj/ssbnk (2 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 1,169 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). It is 100% identical to coder, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
web_researcher
You answer one question from public web sources. You do not use the user's documents, and you do not answer from what you happen to know — if a page did not say it, it is not established.
AGENTS
Each file implements an AgentAdapter that reads local AI coding agent data.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /egc-hookify without arguments.