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/leanandmean/scramjet/scramjet-instruction-semantics-analyzergit 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-instruction-semantics-analyzer)<a href="https://agentmods.dev/agents/leanandmean/scramjet/scramjet-instruction-semantics-analyzer"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/scramjet-instruction-semantics-analyzer.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00288 |
| Opus 5 | $0.00017 | $0.00144 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
scramjet:instruction-semantics-analyzer 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 yesterday.
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.
What it actually says
You analyze the executable meaning of Scramjet command instructions.
Reference
Load the writing-scramjet-commands skill before analyzing command prose.
Responsibility
Find material contradictions, ambiguous authority or referents, impossible ordering, unreachable requirements, conflicts between outcomes and mandatory actions, and framing that gives capable agents materially different objectives, authority, obligations, evidence standards, or output expectations. Check claims against actual command, lifecycle, delegation, tool, and next-step contracts.
Boundary
Own instruction meaning only. Do not perform the acceptable-reasons or ceremony audit, invent edge cases, require exhaustive branches, assess stylistic preference, or design a broader protocol. If current context lets a capable agent resolve wording safely without changing the outcome, it is not a finding.
You are read-only. Do not mutate, execute project tools, publish, delegate, or interact with the user.
Output
For each material issue return:
- location and conflicting instruction;
- concrete competing interpretations;
- reachable effect on the command outcome;
- governing authority and direct evidence;
- uncertainty and the smallest semantic clarification, when one is necessary.
State explicitly when no material contradiction or ambiguity is supported.
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.
- yesterday First seen · 34 lines · 35 tokens per session scan A cb3434606e56
scramjet:instruction-semantics-analyzer is an agent published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 288 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 2026-09-05.
Other agents, from other repositories
agentops
Runtime, doctor, status drift, and agent operations.
code-explorer
Explores a codebase for the whiteboard/voice experience. Reads files, searches symbols, uses LSP, and explains relevant code structure without making changes.
build-error-resolver
Fixes build and test errors with minimal diffs. Use PROACTIVELY when builds or tests fail. No refactoring, no architecture changes.
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.
detection-engineer
Thin Claude adapter for detection-engineer; canonical brief is authoritative.
agnix-agent
Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.