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/ne11nn/cantos-plugin/startgit clone --depth 1 https://github.com/ne11nn/cantos-pluginWhat 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 | $0.00021 | $0.00370 |
| Opus 5 | $0.00010 | $0.00185 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
start 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
You are now running the Cantos system for THIS session only, from the plugin's bundled copy. Nothing is written to the user's project.
- Read
${CLAUDE_PLUGIN_ROOT}/system/CLAUDE.mdin full. It is the orchestrator's operating contract. Adopt it as your instructions for the rest of this session, with two adaptations because you are running from the plugin rather than a scaffolded checkout:- Skip the First-Run Setup gate. That gate personalizes a writable checkout; this run is ephemeral and read-only. Do not look for or act on the
<!-- SETUP-NOT-DONE -->marker, and do not write tocontext/. - All system paths resolve under
${CLAUDE_PLUGIN_ROOT}/system/. Read an assistant's brain at${CLAUDE_PLUGIN_ROOT}/system/.assistants/<name>/<name>.md, references at${CLAUDE_PLUGIN_ROOT}/system/references/..., the registry at${CLAUDE_PLUGIN_ROOT}/system/registry/index.md, and so on. The user's own project files stay untouched unless they ask you to work on them.
- Skip the First-Run Setup gate. That gate personalizes a writable checkout; this run is ephemeral and read-only. Do not look for or act on the
- Then act on the user's request exactly as Cantos would: assess the domain, morph into the right assistant by reading its brain file from the bundled system, or orchestrate across assistants, then proceed.
- If the user wants Cantos to persist and evolve in this project (so
/wrapand brain-file updates stick across sessions), tell them to run/cantos:init, which scaffolds the full writable system into the project.
Read the orchestrator file now, then handle the user's request: $ARGUMENTS
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 · 14 lines · 21 tokens per session scan A 219e32cf86a5
start is a command published in the GitHub repository ne11nn/cantos-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 370 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
orra
Start or attach the Orra standing orchestrator background agent.
multi-agent-optimize
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated agent-based optimization. Leveraging cutting-edge AI orchestration techniques, this tool provides a comprehensive approach to performance engineering across multiple…
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
xdo
Direct development by the Main Agent.
lavra-work-teams
Work on multiple beads with persistent worker teammates that self-organize through a ready queue.