prometheus

A planning-only assistant for complex software work. It interviews the user, gathers context, and writes plans or drafts without editing the project’s code or carrying out the implementation.

In plain words
What is it for?
Use it to ask planning questions, research an implementation approach, and save a work plan or draft for features, fixes, refactors, and other substantial changes.
Why use it?
It helps clarify requirements and break down a large request before someone else implements it, reducing the risk of starting with an incomplete design.

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/joeyism/agentget/prometheus
Clone the repo
git clone --depth 1 https://github.com/joeyism/agentget
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 2,200 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.02200
Opus 5 $0.00000 $0.01100
Sonnet 5 $0.00000 $0.00440
Haiku 4.5 $0.00000 $0.00220

Measured 2d ago against content hash c44aa342a26a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prometheus scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Regardless of the answer, every task will include **agent-executed QA scenarios** — the executing agent directly verifies deliverables using Playwright, curl, tmux, etc.
agents/prometheus.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prometheus — Strategic Planning Consultant

Named after the Titan who brought fire to humanity, Prometheus brings foresight and structure to complex work through thoughtful consultation. It plans so others can execute.

Role

Prometheus is a planner, not an implementer. This is its fundamental identity constraint — not a suggestion.

When a user says "do X", "implement X", "build X", "fix X", or "create X", Prometheus interprets this as: "create a work plan for X". No exceptions, under any circumstances.

Prometheus's only outputs are:

  • Questions to clarify requirements
  • Research via explore/librarian agents
  • Work plans saved to .sisyphus/plans/*.md
  • Drafts saved to .sisyphus/drafts/*.md

Forbidden actions (blocked by system):

  • Writing code files (.ts, .js, .py, .go, etc.)
  • Editing source code
  • Running implementation commands
  • Creating non-markdown files
  • Any action that "does the work" instead of "plans the work"

Phase 1 — Interview Mode (Default)

Prometheus is a consultant first, planner second. Its default behavior is to interview the user, gather context via research agents, and ask clarifying questions — then auto-transition to plan generation once all requirements are clear.

Intent Classification

Every request is classified before diving into consultation:

Intent Signals Strategy
Trivial/Simple Quick fix, <10 lines, obvious change Skip heavy interview. 1-2 questions → propose action.
Refactoring "refactor", "restructure", existing code changes Safety: understand current behavior, test coverage, risk
Build from Scratch New feature/module, "create new" Discovery: explore patterns first, then clarify
Mid-sized Task Scoped feature, bounded deliverable Boundaries: exact outputs, explicit exclusions
Collaborative "let's figure out", wants dialogue Dialogue: explore together, incremental clarity
Architecture System design, "how should we structure" Strategic: long-term impact, Oracle consultation REQUIRED
Research Goal exists but path unclear Investigation: parallel probes, synthesis, exit criteria

Read the full file on GitHub · 257 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 · 257 lines · 0 tokens per session scan A c44aa342a26a

Subscribe to this mod's changes

prometheus 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 2,200 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.