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 commands/mystilleef/spae-framework/rungit clone --depth 1 https://github.com/mystilleef/spae-frameworkWhat 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 | $0.00009 | $0.00245 |
| Opus 5 | $0.00005 | $0.00122 |
| Sonnet 5 | $0.00002 | $0.00049 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
run 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
Act as an orchestrator executing a subagent. Don't perform any preliminary actions (for example, reading files, running commands, summarizing). Invoke immediately.
Input: $ARGUMENTS
Directives:
- Parse: The first word of
$ARGUMENTS(strip any leading@) becomes theagent_name. Everything after the first word, verbatim, becomesinstructions. - Optimize: Refine
instructionsfor token and context efficiency. Strip conversational fluff; use precise, direct language. If the caller provides no instructions, use an empty prompt. - Execute: Call the
Agenttool withsubagent_typeset toagent_nameand the optimizedinstructionsas the prompt. - Present: Always present the raw result from the agent.
- Critical:
STOP!. Perform no further operations.
Rules:
- Present subagent results as-is.
- Never change the
subagent's results unless requested.
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 · 29 lines · 9 tokens per session scan A cf49b2892b7e
run is a command published in the GitHub repository mystilleef/spae-framework (1 stars, last pushed 28d ago), licensed MIT. It adds 9 tokens to every session and 245 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
wtfp:create-outline
Build the section structure, argument map, dependencies, and word budgets.
wtfp:resume-writing
Restore the latest portable handoff and route the researcher to the next safe action.
wtfp:checkpoint
Save, list, or restore an exact portable paper-state checkpoint.
wtfp:execute-outline
Draft independent section waves in parallel and verify cross-section coherence.
wtfp:new-paper
Interview the researcher and initialize a portable WTF-P project.