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 skills/tu11aa/squadrant/side-sessionnpx skills add tu11aa/squadrant --skill side-sessiongit clone --depth 1 https://github.com/tu11aa/squadrantWhat 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 | $0.00046 | $0.01113 |
| Opus 5 | $0.00023 | $0.00557 |
| Sonnet 5 | $0.00009 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
side-session 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Side-Sessions
A side-session is a dedicated tab with fresh context running the captain model (opus), loaded with a role-specific template. It runs outside the crew/daemon lifecycle — no CREW IDLE/DONE noise back to the primary captain. Its only upward signal is an explicit, user-confirmed structured handoff.
Spawn a side-session
# Research a topic, discuss an idea, produce a spec or GH issue
squadrant side spawn <project> "<topic>" --role research
# Debug a bug in an isolated scratch worktree
squadrant side spawn <project> "<topic>" --role debug
Options:
--name <name>— custom tab name (default: autoside-N)--direction <tab|right|down|left|up>— placement (default: tab)--agent <claude|opencode>— agent to use (default: claude)--topic-file <path>— read topic from a file
Manage side-sessions
squadrant side list <project> # see live side tabs
squadrant side send <project> <name> "<follow-up>" # send a follow-up turn
squadrant side close <project> <name> # close when done
Role: research
Can: Read code/docs, run read-only commands, create GH issues, write specs/plans. Cannot: Edit source code, spawn crews, merge/ship changes.
The session works in fresh context and produces artifacts (specs, GH issues, analysis). When done, it asks the user to confirm before sending a structured handoff to the primary captain.
Role: debug
Can: Read code/docs, run code and tests, edit source — but scratch only in its isolated worktree (instrumentation, logging, a failing test to pinpoint the root cause). Cannot: Edit source outside the scratch worktree, spawn crews, merge/ship changes.
The debug role creates an isolated scratch git worktree on spawn. Edits made there are never shipped — the draft patch lives on the scratch branch and is referenced in the handoff for a crew to implement cleanly. Close prunes the scratch worktree.
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 · 114 lines · 46 tokens per session scan A 7912a4011429
side-session is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,113 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 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
kagent-dev
Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).