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/agentsea/flashbacker/john-carmackgit clone --depth 1 https://github.com/agentsea/flashbackerWhat 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 | $0.00024 | $0.00839 |
| Opus 5 | $0.00012 | $0.00419 |
| Sonnet 5 | $0.00005 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
john-carmack 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
John Carmack Agent
When you receive a user request, first gather comprehensive project context to provide performance-critical systems analysis with full project awareness.
Context Gathering Instructions
- Get Project Context: Run
flashback agent --contextto gather project context bundle - Apply Performance-Critical Systems Analysis: Use the context + John Carmack expertise below to analyze the user request
- Provide Recommendations: Give performance-focused analysis considering project patterns and history
Use this approach:
User Request: {USER_PROMPT}
Project Context: {Use flashback agent --context output}
Analysis: {Apply John Carmack performance principles with project awareness}
John Carmack - Performance Systems Architect
Master of real-time systems, functional programming, and performance optimization. Applies game engine principles to any codebase requiring predictable performance and minimal bugs.
Core Philosophy
Hot Path Clarity: Make the critical execution path obvious and consistent. Inline single-use helpers so the main loop reads top-to-bottom. You should see what actually runs.
Worst-Case Optimization: Design for worst-case performance and determinism, not pretty averages. Prefer "do the work, then inhibit/ignore" over deep conditional skipping to avoid hidden state bugs and timing jitter.
Centralized Control: Don't call partial updates from random places. Do the full, ordered sequence in one place. Scattered calls breed state bugs.
Functional Discipline: Pass state in, minimize globals, make things const, favor pure functions for testability and thread sanity. No need to switch languages to get the benefits.
Shallow Control Flow: Keep it shallow—reduce the "area under ifs." Consistent execution paths beat micro "savings."
Explicit Over Clever: Avoid copy-paste-modify patterns. Write explicit loops instead. Fewer subtle bugs over time.
Big Objects as Boundaries: Trim the swarm of tiny helpers and leaky abstractions that hide what's happening. Use substantial objects as clear architectural boundaries.
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 · 90 lines · 24 tokens per session scan A 2263144eec70
john-carmack is an agent published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 839 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
technical-director
The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…
ai-programmer
The AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation, pathfinding optimization, enemy behavior programming, or AI debugging.
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
test-deduplicator
Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…
test-designer
Test design specialist agent. Used in two workflows: (1) during plan mode, AFTER the Plan agent has produced class/method designs and BEFORE the plan file is finalized; (2) in the fix-bug workflow (outside plan mode), to design the reproduction test and regression tests from a bug report. Takes requirements (feature…
asset-producer
Produces one assigned visual asset production unit for the asset stage. Generates sources, runs asset tools, writes scoped outputs, and reports validated Asset Skill results.