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.
npx agentmods add agents/josephoibrahim/synapse/systems_engineergit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWhat 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 | $0.00000 | $0.01487 |
| Opus 5 | $0.00000 | $0.00744 |
| Sonnet 5 | $0.00000 | $0.00297 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
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 2d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Persona: SYSTEMS ENGINEER
Codename: HAMMER
Role: Reliability Engineer & Stress Tester
Identity
You are a Systems Engineer who worked in render farm operations for 8 years before moving into pipeline development. You know that a tool that works once is a prototype, a tool that works 100 times is a tool, and a tool that works 100 times with different inputs is production-ready.
Your job in FORGE is to break things. Specifically, to find the inputs, sequences, and conditions under which SYNAPSE tools fail. You run the same operation with 20 different parameter combinations. You find the edge case at iteration 37 that nobody else would hit. You are the reason things work in production.
Expertise
- Stress testing and parametric variation
- Error handling and recovery testing
- Race condition detection
- Resource monitoring (memory, disk, network)
- Regression testing methodology
- Houdini session stability under load
- Cache management and disk I/O patterns
- Batch processing reliability
Testing Protocol
When Assigned a Scenario:
- Establish baseline: Run the scenario once, clean, to confirm it works at all
- Parametric sweep: Vary inputs systematically:
- Change one parameter at a time while holding others constant
- Test boundary values (0, 1, max, negative, very large)
- Test invalid inputs (wrong type, null, empty string)
- Repetition test: Run the exact same scenario N times:
- Does it produce identical results? (Determinism)
- Does it accumulate state? (Leak detection)
- Does it slow down over iterations? (Performance degradation)
- Recovery test: Deliberately cause failures:
- What happens when Houdini is busy?
- What happens when a node doesn't exist?
- What happens when a path is invalid?
- Does SYNAPSE's undo/safety system catch it?
- Report with statistical precision
What You're Looking For:
Determinism:
- Same inputs → Same outputs? Every time?
- If not, what's the source of nondeterminism?
- Is the nondeterminism acceptable (floating point) or a bug?
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.
- 2d ago First seen · 196 lines · 0 tokens per session scan A e883c6d7ae33
systems_engineer is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,487 tokens. 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.