_SCHEMA

A definition format for subagents, where each JSON file describes an agent's role, model, instructions, tools, triggers, and measures of success.

In plain words
What is it for?
Use it when creating or reviewing agent definitions, including their responsibilities, allowed tools, skills, dispatch signals, and success metrics.
Why use it?
It gives the team a consistent way to configure and dispatch specialized agents instead of defining them ad hoc.

Agent

Install

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.

agentmods
npx agentmods add agents/itsribbz/godspeed/_schema
Clone the repo
git clone --depth 1 https://github.com/itsribbZ/Godspeed
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,129 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01129
Opus 5 $0.00000 $0.00564
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 2d ago against content hash 0714cd9baed5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_SCHEMA 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.

plugins/godspeed/automations/director/agents/_SCHEMA.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Schema (v1.0)

Real subagent persona definitions. Each <name>.json defines one agent — its system prompt, tool grants, skill wrappers, trigger signals, success metrics, and per-agent learnings file.

Required fields

Field Type Description
name string Unique agent identifier (snake_case). Becomes the JSON filename.
division string Owning division (research, debug, etc.).
role string One-line role summary (≤120 chars).
model string haiku / sonnet / opus — invocation model.
system_prompt string Full persona prompt. Includes: charter, sacred-rule overrides, reasoning style, output format.
tool_grants string[] Allowed Claude Code tools (Read, Edit, Bash, Grep, etc.). Informational; enforced at dispatch.
skill_wrappers string[] Existing skills this agent reaches into for context. Loaded as context, not invoked.
trigger_signals object[] Phrase + weight signals for sub-dispatch within division. [{"phrase": "research", "weight": 0.85}, ...]
success_metrics object Per-agent KPIs (target values measurable from telemetry).
_learnings_path string Relative path to per-agent _learnings.md.
version string Schema version (currently 1.0).

Optional fields

Field Type Description
max_thinking_budget int Sonnet/Opus extended thinking budget in tokens. Default per-tier.
tool_result_truncation_chars int Truncate tool output to N chars before next iteration (saves cache cost).
anti_signals object[] Negative phrase weights (suppresses dispatch when matched).
sacred_rule_overrides string[] Agent-specific sacred-rule reinforcements.
output_contract object Structured output expectations (verdict, citations, etc.).
parent_skill string If agent is a focused persona of an existing skill, name it.
created string ISO date created.
scan_date string Last review date.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 2d ago First seen · 86 lines · 0 tokens per session scan A 0714cd9baed5

Subscribe to this mod's changes

_SCHEMA is an agent published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,129 tokens. 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.