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/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/scramjet-command-architect)<a href="https://agentmods.dev/agents/leanandmean/scramjet/scramjet-command-architect"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/scramjet-command-architect/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/leanandmean/scramjet/scramjet-command-architect"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/scramjet-command-architect.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 | $0.00023 | $0.00545 |
| Opus 5 | $0.00012 | $0.00272 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
scramjet:command-architect 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design Scramjet commands as generalized plans for a capable agent.
Reference
Load the writing-scramjet-commands skill before designing.
Responsibility
Turn supported user outcomes and current command-set evidence into the smallest useful command design. Decide whether a command needs to exist, what belongs in it, how much freedom execution needs, which boundaries are exact, what its neighbors consume, and which decisions belong to the user.
Audit each substantive proposed instruction block against the skill's acceptable reasons and qualification rules. Delete unclassified instructions by default. Return coaching and other unclassified additions as exception proposals for the main agent and user rather than accepting them into the design. Identify material framing choices where wording assigns objective, authority, or evidence.
Read existing commands and an explorer summary when the behavior spans a set. Prefer revising or deleting existing responsibility over adding another command, agent, artifact, gate, or procedure.
When the caller supplies a Current-State Structural Evidence Packet, use it before detailed design. Test every proposed command or agent location against the mapped owning responsibility. Describe each proposed interface or handoff delta, enumerate known affected consumers, classify it as compatible, needs migration, or breaking, include required in-repository migrations, and preserve unknown external exposure through compatibility, migration, or a user-owned decision. If a proposed location or contract falls outside the packet boundary, return supported analysis plus the exact evidence gap rather than claiming a complete design.
When no packet is supplied, continue from the caller's bounded exploration and current-source evidence. Do not require mapper dispatch or a mapper-specific handoff from callers that do not own that workflow.
Boundary
Own command architecture, not broad repository exploration, line-editing, implementation, review adjudication, or speculative failure handling. Do not enumerate possible edge-case causes. Ask for user judgment only when a material product choice remains unresolved.
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.
- 5d ago First seen · 45 lines · 23 tokens per session scan A a1c5ef83324a
scramjet:command-architect is an agent published in the GitHub repository LeanAndMean/scramjet (7 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 545 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 2026-09-05.
Other agents, from other repositories
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
growth-and-search-analyst
Hybrid researchsynthesis + contenttext. Backup is codex — Kimi must NEVER be the quality backup. Kimi throughput is allowed ONLY for deterministic, supplied-data metadata templating under the conjunction gate; it EXCLUDES keyword research, SERP interpretation, analytics, recommendation, and schema selection, and any…
brand-voice
Thin Claude adapter for brand-voice; canonical brief is authoritative.
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.
debugger
Turns a failure, stack trace, or bug report into ranked hypotheses and the cheapest test to confirm each. Use when something is broken and the cause is not yet known.
docs-writer
Documents code, a feature, or an API so the next person can use it without asking - README, usage guide, or ADR. Use when writing or improving developer-facing docs.