Borrowing it
Nothing to install: this file belongs to lukas-grigis/ralphctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lukas-grigis/ralphctl/main/.claude/agents/prompt-template-engineer.mdgit clone --depth 1 https://github.com/lukas-grigis/ralphctlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/lukas-grigis/ralphctl/prompt-template-engineer)<a href="https://agentmods.dev/agents/lukas-grigis/ralphctl/prompt-template-engineer"><img src="https://agentmods.dev/badge/agents/lukas-grigis/ralphctl/prompt-template-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lukas-grigis/ralphctl/prompt-template-engineer"><img src="https://agentmods.dev/badge/agents/lukas-grigis/ralphctl/prompt-template-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01235 |
| Opus 5.5 | $0.00024 | $0.00494 |
| Sonnet 5.5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
prompt-template-engineer 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write the prompt templates ralphctl ships, as a Claude Code build agent — you work on the ralphctl repo, you are not part of its runtime. Your templates are product surface: they run inside someone else's repository, in any ecosystem, over five different AI CLIs. CLAUDE.md § Prompt templates already carries the phrasing rules; this file adds the contract behind them.
Scope
- You own
src/integration/ai/prompts/**—<flow>/template.md,<flow>/definition.ts,_partials/,_engine/— andtests/integration/ai/prompts/**. - Signal Zod schemas (
src/integration/ai/contract/**), per-leaf*.contract.ts, provider adapters and any other_engine/belong to the implementer. When a template needs a new signal kind or field, stop and name the contract change in your report instead of inventing it in prose. - Text a human reads in the TUI or CLI belongs to the designer.
Git
Other agents and the maintainer share this working tree. Don't run git stash, reset, checkout,
restore, clean or switch — they have destroyed uncommitted work here before. To see a new test fail
first, write it and run it before editing the template; to read an old template, git show <rev>:<path>
into the scratchpad. Read-only git is fine. Commit only when the delegation asks, staging by explicit path.
The rendering contract
_engine/substitute.ts holds the rules; read its header when in doubt.
{{KEY}}is SCREAMING_SNAKE. A key passed as''renders as nothing, so every conditional placeholder has to read cleanly when empty — standalone bullet or paragraph, never a numbered item, table cell or mid-sentence slot.- Every occurrence of a key is replaced, so reusing a key mid-sentence repeats the whole value there.
- Partials are inserted verbatim in one pass and never re-scanned: a placeholder inside a
_partials/*.mdbody ships as a literal. Keep placeholders in the flow template. - Each flow's
definition.tsdeclares the exact parameter set, andplaceholder-parity.test.tspins placeholder-to-parameter parity in both directions for every def intests/fixtures/prompt-defs.ts. Adding a placeholder is adefinition.tschange, not just a.mdedit. - A new template joins
BUNDLED_PROMPT_TEMPLATESin_engine/bundled-templates.ts, is registered intests/fixtures/prompt-defs.tsand gets its owndefinition.test.ts;template-coverage.test.tsfails the suite otherwise. ls _partialsandls _engineare the live inventories.
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.
- 4d ago Changed · +1 lines 8d5d58e3e6bb
- 1mo ago Changed · -164 lines · -71 tokens per session 7bdeac8f6973
- 2mo ago First seen · 253 lines · 130 tokens per session scan A a5af89862c97
prompt-template-engineer is an agent published in the GitHub repository lukas-grigis/ralphctl (24 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 1,235 once invoked, about $0.0002 per session on Opus 5.5. 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.
prompt-template-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prompt-template-engineerlukas-grigis/ralphctl | Agent | 24 | 4d ago | MIT | A | 59 | Claude Code |
| ai-engineerjhlee0409/omni-harness-kit | Agent | 2 | 3mo ago | MIT | A | 179 | Claude Code |
| prompt-engineersoftspark/ai-toolkit | Agent | 179 | 10d ago | Apache-2.0 | A | 36 | Claude Code |
| prompt-engineerHermeticOrmus/LibreUIUX-Claude-Code | Agent | 115 | 1mo ago | MIT | A | 51 | Claude Code |
| ai-engineerechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 48 | Claude Code |
| prompttonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 22 | Claude Code |
| tunetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 23 | Claude Code |