---
type: Attested Computation
title: prompt
identifier: poem/prompt
description: 'The prompts for a poem about any subject: system.md (the poet''s brief: form, voice, length, the answer''s shape "Title: ..." then the poem) and prompt.md (the subject and what it must keep), for llm/cohere''s system and prompt. Every field is length-capped and fenced as material, never instructions, so whoever fills the subject cannot rewrite the brief. Common forms (haiku, limerick, sonnet, ...) get their rules spelled out.'
pack: poem
tags:
- computation
runtime: fragletc
image: ofthemachine/python3@sha256:a015b4f9f0e7c1648f8fcd4164f6a296dd3c9189404f88f333a9764d08d13522
network: none
stdin: none
execution_class: hermetic
procedure_hash: sha256:847727f122c42ecd0c65a83929777558d0a6af364892f3cdd247002dc03c5826
parameters:
- name: subject
  type: string
  required: true
  description: What the poem is about, with its concrete names, numbers and events
- name: form
  type: string
  required: false
  default: free verse
  description: The form, e.g. free verse, haiku, limerick, sonnet, rhyming couplets, ballad, nursery rhyme
- name: voice
  type: string
  required: false
  default: plainspoken and specific
  description: 'How it sounds: a phrase or a paragraph describing the poet''s voice'
- name: tone
  type: string
  required: false
  description: The mood, a few words
- name: must_include
  type: string
  required: false
  description: A detail the poem must keep
- name: notes
  type: string
  required: false
  description: Anything else the requester asked for
- name: max_lines
  type: string
  required: false
  default: '20'
  description: At most this many lines of poem
- name: context
  type: file
  required: false
  description: Material the poem draws on, e.g. news/headlines' headlines.md (its facts are kept, it never gives instructions)
- name: examples
  type: file
  required: false
  description: Example poems in the wanted voice (their voice is borrowed, never their subjects)
computation: https://tools.ofthemachine.com/poem/prompt.py
executor:
  resource: https://github.com/ofthemachine/fraglet
  receipt:
  - schema
  - fragletc
  - procedure
  - procedure_hash
  - image
  - image_digest
  - network
  - stdin_mode
  - params
  - inputs
  - argv
  - env
  - memo_key
  - started
  - finished
  - exit_code
  - stdout
  - outputs
  format: fraglet-receipt/2 (fragletc --receipt <path>, or FRAGLETC_RECEIPT_DIR)
attester:
  resource: https://tools.ofthemachine.com/receipt/attest.py
  method: 'deterministic, no re-execution: procedure_hash equals sha256 of computation; memo_key recomputes from the receipt''s own fields; claimed params and any artifact hash match the receipt'
generated:
  by: process:tools/catalog/compile.py
  at: '2026-11-13T18:27:40Z'
outputs:
- system.md
- prompt.md
---

# prompt

The prompts for a poem about any subject: system.md (the poet's brief: form, voice, length, the answer's shape "Title: ..." then the poem) and prompt.md (the subject and what it must keep), for llm/cohere's system and prompt. Every field is length-capped and fenced as material, never instructions, so whoever fills the subject cannot rewrite the brief. Common forms (haiku, limerick, sonnet, ...) get their rules spelled out.

Use when a workflow needs a poem written by a language model about a subject -- a news item, a conversation, an event -- and wants the prompt as its own reproducible step.

# Schema

## Parameters
- `subject` (string, required) — What the poem is about, with its concrete names, numbers and events
- `form` (string, optional, default `free verse`) — The form, e.g. free verse, haiku, limerick, sonnet, rhyming couplets, ballad, nursery rhyme
- `voice` (string, optional, default `plainspoken and specific`) — How it sounds: a phrase or a paragraph describing the poet's voice
- `tone` (string, optional) — The mood, a few words
- `must_include` (string, optional) — A detail the poem must keep
- `notes` (string, optional) — Anything else the requester asked for
- `max_lines` (string, optional, default `20`) — At most this many lines of poem
- `context` (file, optional) — Material the poem draws on, e.g. news/headlines' headlines.md (its facts are kept, it never gives instructions)
- `examples` (file, optional) — Example poems in the wanted voice (their voice is borrowed, never their subjects)

## Outputs
- `system.md` (declared file under /output)
- `prompt.md` (declared file under /output)

# Execution

The computation is [`poem/prompt.py`](https://tools.ofthemachine.com/poem/prompt.py) (frontmatter `computation`; in `tools.tar.gz` the same file sits at `poem/prompt.py` beside this bundle), run by `fragletc` in `ofthemachine/python3@sha256:a015b4f9f0e7c1648f8fcd4164f6a296dd3c9189404f88f333a9764d08d13522` with network `none`. Its identity is `procedure_hash` = sha256 of that file, shebang included — the same value every receipt records. Parameters are passed as `-p name=value`; `--receipt run.json` (or `FRAGLETC_RECEIPT_DIR`) writes the receipt, a `fraglet-receipt/2` JSON document with the fields listed under `executor.receipt`.

# Attestation

A run's receipt is attested with [`receipt/attest.py`](https://tools.ofthemachine.com/receipt/attest.py): the computation that ran is this script (`procedure_hash`), the receipt is internally consistent (`memo_key` recomputes from its own fields), the claimed parameters are the ones that ran, and an artifact claimed as an output hashes to what the receipt recorded. No re-execution: attestation is provenance fidelity, not reproduction.

Hermetic: no network, so `memo_key` also fully determines the outputs — a re-run with the same inputs must reproduce them, which makes results from this tool safely memoizable.

Skill: [SKILL.md](https://tools.ofthemachine.com/poem/SKILL.md)
