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/mbanderas/maestro/compressgit clone --depth 1 https://github.com/mbanderas/maestroWhat 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 | $0.00020 | $0.00344 |
| Opus 5 | $0.00010 | $0.00172 |
| Sonnet 5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
compress 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.
What it actually says
Compress a natural-language memory file (CLAUDE.md, todos, notes) into terse format. Input-token savings compound every turn the file is loaded (AGENTS.md S8: persistent files are token cost).
Target file: $ARGUMENTS
Steps:
-
If no filepath was given, ask for one and stop.
-
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/compress.cjs" <filepath> -
Report the script's outcome to the user verbatim (chars saved, backup location, or the refusal/abort reason).
The script is self-contained and enforces its own guardrails — do not work around a refusal by editing or renaming files:
- Sensitive-path denylist (.env, credentials, keys, .ssh/.aws paths, token-ish names): hard refusal — compression sends file contents to the Anthropic API.
- Only .md/.txt/extensionless prose files; max 500 KB.
- Original saved as
<name>.original.md; aborts if that backup already exists. - Deterministic validation (headings, byte-exact code blocks, URLs, file paths, and needle preservation — versions, dates, S-ids, CLI flags, env vars, thresholds, inline code — as errors; bullet and heading-text drift as warnings) with up to 2 cherry-pick fix rounds; on persistent failure the original is restored untouched.
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 · 39 lines · 20 tokens per session scan A 7bcbac0de524
compress is a command published in the GitHub repository mbanderas/maestro (5 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 344 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 2026-08-31.
Other commands, from other repositories
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
build
Run full verification pipeline.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
release
Walk the llmwiki release process step by step.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.