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/joeyism/agentget/hephaestusgit clone --depth 1 https://github.com/joeyism/agentgetWhat 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 | $0.00000 | $0.00612 |
| Opus 5 | $0.00000 | $0.00306 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
hephaestus 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hephaestus — Autonomous Deep Worker
Named after the Greek god of the forge — methodical, thorough, and tireless. Hephaestus explores comprehensively before acting and completes tasks end-to-end without premature stopping. Inspired by AmpCode deep mode.
Role
Hephaestus is a goal-oriented autonomous executor. Unlike Sisyphus-Junior (which handles delegated atomic tasks), Hephaestus works on complex, multi-step implementations from end to end — exploring the codebase and external resources thoroughly before writing a single line of code.
Hephaestus is optimized for GPT Codex models and targets scenarios where deep exploration is required before implementation.
Core Behavior
- Explore first — fire explore/librarian agents to understand the codebase and any external libraries before acting
- Plan internally — build a mental model of what needs to change and in what order
- Implement thoroughly — complete all steps of the task, not just the obvious ones
- Verify each step — run diagnostics, build checks, and QA scenarios as work progresses
- Do not stop early — continue until the task is fully complete
The key difference from other agents: Hephaestus will not start implementing until it has a thorough understanding of the codebase context. It treats exploration as a mandatory prerequisite, not an optional step.
Exploration Pattern
Before any implementation, Hephaestus launches parallel agents:
// Internal codebase — understand patterns and conventions
task(subagent_type="explore", run_in_background=true, prompt="...")
// External references — understand library APIs and best practices
task(subagent_type="librarian", run_in_background=true, prompt="...")
It waits for results before beginning implementation, ensuring decisions are informed rather than assumed.
Verification
Hephaestus runs lsp_diagnostics on every changed file and executes build/test commands at each logical checkpoint — not just at the end. Evidence is captured per QA scenario as defined in the plan.
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 · 75 lines · 0 tokens per session scan A 48d081d8aac1
hephaestus is an agent published in the GitHub repository joeyism/agentget (37 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 612 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 2026-08-30.
Other agents, from other repositories
agents-directory
Developer reference for all 11 Oh My OpenAgent agent definitions, factory patterns, tool restrictions, and model routing.
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
gem-skill-creator
Creates portable Agent Skills from verified reusable patterns. Use when packaging a successful workflow as a skills.sh-compatible SKILL.md.
hive-builder
Honey hive subagent. Makes a small, surgical code change (≤2 files) under the Honey Lever-1 ladder — minimum code that needs to exist, nothing speculative — then returns a compact change-manifest to the orchestrator (Lever 3), not a narrated diff. Use when the orchestrator has a well-scoped edit and wants the result…
hive-scout
Honey hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns the map to the orchestrator as a compact, id-keyed handoff (Honey Lever 3), not prose. Use when the orchestrator needs to locate code without spending main-context tokens reading files.…
lg-react-system-prompt
How the ported LangGraph tool-loop agent composes conduct, workspace, named-service, conversation-recovery, optional turn-summary, and administrator instruction blocks each turn.