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 skills add LeanAndMean/scramjet --skill writing-scramjet-commandsgit 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/skills/leanandmean/scramjet/writing-scramjet-commands)<a href="https://agentmods.dev/skills/leanandmean/scramjet/writing-scramjet-commands"><img src="https://agentmods.dev/badge/skills/leanandmean/scramjet/writing-scramjet-commands/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/skills/leanandmean/scramjet/writing-scramjet-commands"><img src="https://agentmods.dev/badge/skills/leanandmean/scramjet/writing-scramjet-commands.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 | $0.00027 | $0.02454 |
| Opus 5 | $0.00014 | $0.01227 |
| Sonnet 5 | $0.00005 | $0.00491 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
writing-scramjet-commands 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 7d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Scramjet Commands
Mental model
A Scramjet command is a generalized plan executed by a capable agent with user-supplied context. It is not a natural-language program and should not encode every branch the agent might encounter.
State the destination, controlling boundaries, and necessary handoffs. Let the agent choose tactics from current context.
Informed alignment
User-input and approval gates align the user and agent; they are not obstacles to clear. The main agent owns compressing its larger working context so the user can decide without reconstructing the investigation. Agreement without relevant understanding is not alignment.
Ask when:
- the user owns a product, scope, risk, preference, or authorization decision;
- necessary information is unavailable;
- conflicting authority cannot be resolved safely;
- a coaching or unclassified instruction exception requires approval;
- consequential effects require informed authorization.
Do not ask when current authority, safe investigation, or capable agent judgment resolves the matter. Ritual confirmation and transferring ordinary analysis to the user are command defects.
Before a consequential ask, provide proportionate context: the decision, why the user owns it, evidence and uncertainty, meaningful options, consequences, and a recommendation with its assumptions when appropriate. Do not infer approval from silence, generic prior consent, plan acceptance, or a neighboring decision. Do not manufacture urgency or repeatedly present a declined option without new evidence.
What a command should contain
- Purpose and outcomes: the user- or caller-visible result.
- Authority: the inputs, decisions, and artifacts that control the work.
- Necessary common-path guidance: process supported by an acceptable reason below.
- Hard boundaries: user decisions, exact consumer contracts, consequential side effects, and real trust or safety constraints.
- Ownership: who investigates, decides, mutates, publishes, and asks the user.
- Handoffs: only the artifact or information a downstream participant needs.
- Completion: observable conditions for a truthful result.
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.
- 7d ago First seen · 233 lines · 27 tokens per session scan A 81bac798bc90
writing-scramjet-commands is a skill published in the GitHub repository LeanAndMean/scramjet (7 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 2,454 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 skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-handoff
Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.
cw-orient
Use at the start of any Codewhale work session, or when unsure which checkout, branch, or worktree is authoritative: establish live repo truth before reading a plan or editing a file.