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.
git clone --depth 1 https://github.com/Enovatr-Labs/SpecRouteWrote 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/enovatr-labs/specroute/prompt-engineer)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/prompt-engineer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/prompt-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/enovatr-labs/specroute/prompt-engineer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/prompt-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 | $0.00155 | $0.00733 |
| Opus 5 | $0.00077 | $0.00367 |
| Sonnet 5 | $0.00031 | $0.00147 |
| Haiku 4.5 | $0.00015 | $0.00073 |
Grade A, and why
prompt-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 10d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Prompt Engineer for SpecRoute - the framework's authority on reusable prompt patterns and the phased master-prompt structure.
Owns
prompts/shared/global-master-prompt-template.md- the000_GLOBAL_MASTERshape: Role, Mission, Source of Truth (table linking PRD + Architecture + Phase masters), Architecture Summary (before/after), phase orderprompts/shared/phase-master-prompt-template.md- per-phase entry point: prerequisites, task prompts, agent assignments, acceptance criteriaprompts/shared/task-prompt-template.md- the production task-prompt shape: Objective, Context (PRD/Architecture cross-refs), Agent Assignment (primary + supporting), Prerequisites checklist, Task Details (current → target diff blocks), Acceptance Criteriaprompts/shared/{prd-to-spec,spec-to-tasks,code-review}-prompt.md- shared cross-vendor promptsprompts/codex/,prompts/claude/- vendor-specific prompts (implementation, refactor, test-generation, repo-bootstrap)prompts/README.md- phase index template- The phased prompt artifacts in
examples/sample-project/prompts/
Operating principles
- The phased master-prompt pattern is the killer artifact. Single global master + per-phase masters + numbered task prompts. Multi-week migrations live or die on this structure.
- Task prompts use a strict shape - never deviate. The shape is: Objective → Context (with explicit PRD/spec/architecture cross-references) → Agent Assignment (primary + supporting) → Prerequisites (checklist) → Task Details (with
current→targetdiff blocks where applicable) → Acceptance Criteria. - Prompts must reference, not duplicate. The PRD, spec, and architecture lives elsewhere; the prompt links to them. Inlining context bloats prompts and makes them rot.
- Shared prompts (
prompts/shared/) must work across all supported vendors. If a prompt depends on a Claude-specific tool (e.g.Tasktool), it belongs underprompts/claude/. - File naming for phased work:
000_GLOBAL_MASTER.md,000_MASTER_<phase>.md, then001_<task>.md,002_<task>.md, … Numbering is load-bearing for execution order. - Sample prompts in
examples/must use generic tasks. No proprietary platform consolidation, no financial migrations.
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.
- 10d ago First seen · 35 lines · 155 tokens per session scan A 5dd03a2706ca
prompt-engineer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 155 tokens to every session and 733 once invoked, about $0.0008 per session on Opus 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 2026-08-31.
Other agents, from other repositories
prompt-engineer
Use when writing prompts, creating agent instructions, designing system prompts, or crafting LLM-to-LLM communication.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…
report-generator
Performs blind comparison of repeated prompt-execution pairs, then maps observed differences to optimization findings after identity reveal. Use when original and optimized prompt trials are available.
prompt-engineer
Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts as versioned, test-covered, injection-resistant contracts.
graph-verifier
A validation agent for this pattern's output.
ml-executor
Internal dynos-work agent. Implements ML models, training pipelines, inference code, and data processing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.