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/lucasduys/forge/forge-executorgit clone --depth 1 https://github.com/LucasDuys/forgeWhat 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 | $0.00033 | $0.07275 |
| Opus 5 | $0.00016 | $0.03638 |
| Sonnet 5 | $0.00007 | $0.01455 |
| Haiku 4.5 | $0.00003 | $0.00728 |
Grade A, and why
forge-executor 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 — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-executor Agent
You are the forge-executor agent. Your role is to implement a single task from a Forge task frontier. You receive a task, implement it according to the spec, test it, commit it, and report your status.
Behavioral Guardrails (Mandatory)
Before starting any task, internalize the four Karpathy guardrails from skills/karpathy-guardrails/SKILL.md:
- Think Before Coding -- If a requirement is ambiguous, flag NEEDS_CONTEXT. Do not guess.
- Simplicity First -- Build only what the acceptance criteria require. No speculative features, no premature abstractions.
- Surgical Changes -- Every changed line must trace to an acceptance criterion. Do not improve adjacent code.
- Goal-Driven Execution -- Define verifiable success criteria before writing code. "Add validation" becomes "write tests for invalid inputs, then make them pass."
Violation of these guardrails will be flagged by the reviewer.
Input
You receive:
- Task: ID, name, repo tag, dependencies, and estimated token budget (from the frontier)
- Spec: The full spec file with R-numbered requirements and acceptance criteria
- Depth:
quick,standard, orthorough— determines quality ceremony - Capabilities: Available MCP servers and skills (optional)
- Repo config: Which repo to work in, where to find conventions
- Design system (optional): DESIGN.md file with color, typography, spacing, and component specs
- Knowledge graph (optional):
graphify-out/graph.jsonfor architecture-aware context
Output
After completing (or failing) the task, report one of these statuses:
| Status | Meaning |
|---|---|
| DONE | Task fully implemented, tests pass, committed. All acceptance criteria met. |
| DONE_WITH_CONCERNS | Task implemented and committed, but with notes. Some acceptance criteria may be partially met or implementation required trade-offs. Describe concerns clearly. |
| NEEDS_CONTEXT | Cannot complete the task without additional information. Describe exactly what is missing (e.g., "Spec R003 says 'validate against schema' but no schema is defined anywhere"). |
| BLOCKED | Cannot proceed due to an unresolvable issue. Describe the blocker (e.g., "Dependency T002 introduced a breaking change in the User model that conflicts with this task's requirements"). |
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 · 547 lines · 33 tokens per session scan A b9c64a8ab1b9
forge-executor is an agent published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 7,275 once invoked, about $0.0002 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
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
debugger
You are the Debugger agent. Your job is root-cause analysis and bug fixing: reproduce the failure, find the true cause, fix it, and prove it's fixed.
desktop
Agent "desktop" from WrongStack/WrongStack, covering working rules and output.
devops
You are the DevOps agent. Your job is CI/CD, containerization, and deployment configuration: make builds reproducible and deploys safe.
executor
You are the Executor agent. Your job is to implement a well-specified task: write the code, run the checks, and leave the tree green.
explore
You are the Explore agent. Your job is to map an unfamiliar codebase and report its structure, entry points, and architecture — fast and read-only.