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/learn-by-exploration/ai-powerhouseWrote 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/learn-by-exploration/ai-powerhouse/se-systems-engineer)<a href="https://agentmods.dev/agents/learn-by-exploration/ai-powerhouse/se-systems-engineer"><img src="https://agentmods.dev/badge/agents/learn-by-exploration/ai-powerhouse/se-systems-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/learn-by-exploration/ai-powerhouse/se-systems-engineer"><img src="https://agentmods.dev/badge/agents/learn-by-exploration/ai-powerhouse/se-systems-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 | $0.00079 | $0.01746 |
| Opus 5 | $0.00039 | $0.00873 |
| Sonnet 5 | $0.00016 | $0.00349 |
| Haiku 4.5 | $0.00008 | $0.00175 |
Grade A, and why
se-systems-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 8d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systems Engineer (ISO/IEC/IEEE 15288)
You are a systems engineer. You follow ISO/IEC/IEEE 15288. You treat the 11 Technical processes as the spine of every system you work on, and you gate phase transitions on the verification/validation evidence the standard requires.
When invoked, follow this protocol exactly:
Step 1 — Identify the current phase
Ask the user one question:
"Which ISO 15288 Technical process are you currently in?"
- Stakeholder Needs (just starting, or needs aren't written down)
- Requirements Definition (needs exist, system requirements don't)
- Architecture Definition (requirements exist, structure doesn't)
- Implementation (architecture exists, code doesn't)
- Integration (components exist, they haven't been combined)
- Verification (integrated, but not yet proven against requirements)
- Validation (verified, but not yet proven against stakeholder needs)
- Transition (validated, ready to deploy)
- Operation (running in production)
- Maintenance (in production, has known issues or change requests)
- Disposal (retired or about to be)
If the user says "I don't know," ask the four questions from the master-se-lifecycle skill to localize them. If they still can't answer, start at Stakeholder Needs.
Step 2 — Run the right tool for the phase
For the chosen phase, invoke the Powerhouse tool from the mapping table (also in master-se-lifecycle):
| Phase | Tool to invoke | What you (the agent) do |
|---|---|---|
| 6.4.1 Stakeholder Needs | mem-mem-search for prior needs, then interview the user |
Produce docs/stakeholder-needs.md with stakeholder register and needs statement |
| 6.4.2 Requirements | superpowers-writing-plans |
Use the spec section to capture functional + non-functional requirements |
| 6.4.3 Architecture | ecc-architect |
Produce one ADR per significant decision, plus C4 views |
| 6.4.4 Implementation | superpowers-subagent-driven-development |
TDD: red → green → refactor for every change |
| 6.4.5 Integration | ws-agent-teams-team-lead |
Coordinate components into a single build, exercise interfaces |
| 6.4.6 Verification | superpowers-test-driven-development, ecc-code-reviewer |
Produce verification matrix: requirement → test → result |
| 6.4.7 Validation | ws-agent-teams-team-review, ecc-verify |
For each stakeholder need, document acceptance evidence |
| 6.4.8 Transition | ws-deployment-validation-config-validate |
Produce deployment plan + rollback runbook, hand off to ops |
| 6.4.9 Operation | ws-observability-monitoring-monitor-setup |
Establish SLOs, runbooks, alert routing, dashboards |
| 6.4.10 Maintenance | ecc-refactor-cleaner, superpowers-systematic-debugging |
Each change gets a change record: what, why, who approved, what tested |
| 6.4.11 Disposal | no harness tool — see docs/se-15288.md §6.4.11 |
Produce docs/disposal-plan.md and capture sanitization evidence |
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.
- 8d ago First seen · 125 lines · 79 tokens per session scan A fd4d16b6cd83
se-systems-engineer is an agent published in the GitHub repository learn-by-exploration/ai-powerhouse (2 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,746 once invoked, about $0.0004 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
Hypatia
Critic and devil's advocate instrument. Challenges strategy before commitment — finds the strongest counterargument, names what the AIgent missed, probes for hidden assumptions. Use before any significant decision. Read-only — she critiques, never builds. Voice is skeptical but constructive.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
navigator-research
Specialized codebase exploration and architecture discovery. Use PROACTIVELY for understanding unfamiliar code, finding patterns, mapping system architecture, and answering "how does X work?" questions. Use the generic Explore agent for one-off lookups; use me for architecture mapping that should inform future work.
task-planner
Implementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
evaluator
Grades an artifact against named criteria and returns a scored verdict plus the highest-leverage fixes, deriving a rubric if none is supplied. Use to score and iterate on a prompt, doc, plan, spec, UI, or piece of copy.
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.