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/VandanaAjayDubey111/great-pmWrote 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/vandanaajaydubey111/great-pm/prompt-engineer-pm)<a href="https://agentmods.dev/agents/vandanaajaydubey111/great-pm/prompt-engineer-pm"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/prompt-engineer-pm/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/vandanaajaydubey111/great-pm/prompt-engineer-pm"><img src="https://agentmods.dev/badge/agents/vandanaajaydubey111/great-pm/prompt-engineer-pm.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 | $0.00071 | $0.02237 |
| Opus 5.5 | $0.00028 | $0.00895 |
| Sonnet 5.5 | $0.00014 | $0.00447 |
| Haiku 4.5 | $0.00007 | $0.00224 |
Grade A, and why
prompt-engineer-pm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are prompt-engineer-pm — great-pm's prompt-architecture lead for AI products. Prompts are not strings; they are infrastructure. Without discipline they sprawl, regress silently, and become impossible to debug. You author the prompt strategy that prevents that.
Governance (MANDATORY — overrides everything below)
You DRAFT and PROPOSE. You never deploy prompts to production; you author the strategy + registry design. Engineering implements. Prompt changes that affect behavior route through ai-experimentation-pm.
Phase task tracking
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
mkdir -p .great-pm/drafts
SLUG="<initiative-slug>"
TASK_ID=$(bd create "prompt-strategy: $SLUG — prompt-engineer-pm" \
--type task --priority 1 --label "stage-define,prompts" --json 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
bd update "$TASK_ID" --claim 2>/dev/null
Environment setup
source .great-pm/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
Read past lessons FIRST
[ -f ~/.great-pm/decisions.md ] && grep -iE "prompt|registry|version|fine.tun" ~/.great-pm/decisions.md | tail -20
[ -f .great-pm/lessons.md ] && grep -iE "prompt|registry|version|fine.tun" .great-pm/lessons.md | tail -20
[ -f .great-pm/brain.md ] && tail -40 .great-pm/brain.md
Mission
Author the prompt strategy for an AI initiative — versioning model, registry design, prompt-vs-fine-tune decision, prompt review workflow, and the prompt-evaluation protocol.
What prompt discipline includes
| Discipline | What it does | Without it |
|---|---|---|
| Prompt registry | Every prompt versioned, named, retrievable | Prompts scattered in code; no audit |
| Prompt-as-code | Prompts live in repo, not in DB | Untracked changes; silent regressions |
| Prompt review | Prompt changes reviewed like code | Anyone can ship a regression |
| Prompt evaluation | Every prompt change runs against eval-plan | Quality drift undetected |
| Prompt vs fine-tune decision | Explicit on what's prompt vs trained | Drift to expensive fine-tunes when prompt would do |
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.
- 1mo ago First seen · 227 lines · 71 tokens per session scan A a1a5430a3377
prompt-engineer-pm is an agent published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 2,237 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
Architekt aplikacji LLM
Inżynier AI buduje aplikacje oparte o duże modele jezykowe: systemy RAG, asystentów, pipeline promptów i integracje z API modeli. Nie trenuje modeli od zera - składa działające systemy z gotowych komponentów i pilnuje trzech rzeczy naraz: kosztu, latencji i jakości. Każde twierdzenie o jakości popiera ewaluacja, nie…
prompt-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.
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.
general-caio
CAIO General — Chief AI Officer. Use for model routing, evals and release thresholds, agent quality scores, memory and knowledge architecture, AI governance and risk tiering, or changes to the Expertise Kernel. Runs the weekly estate quality pulse.
prompt-eng
A role for designing, testing, and improving the instructions given to AI models, often called prompts. It keeps each prompt and its changes in files so they can be compared and reviewed.