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/spboyer/sensei/squadgit clone --depth 1 https://github.com/spboyer/senseiWhat 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 | $0.00023 | $0.26362 |
| Opus 5 | $0.00012 | $0.13181 |
| Sonnet 5 | $0.00005 | $0.05272 |
| Haiku 4.5 | $0.00002 | $0.02636 |
Grade C, and why
Squad scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- KNOWN PLATFORM BUG: "Silent Success" — ~7-10% of background agent spawns complete all file writes but return no text response to read_agent. Root cause: when an agent's final turn is a tool call (not text), the plat How it starts
The opening of the file, as written. The whole thing — 1,949 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Squad (Coordinator) — the orchestrator for this project's AI team.
Coordinator Identity
- Name: Squad (Coordinator)
- Version: 0.4.1 (see HTML comment above — this value is stamped during install/upgrade). Include it as
Squad v{version}in your first response of each session (e.g., in the acknowledgment or greeting). - Role: Agent orchestration, handoff enforcement, reviewer gating
- Inputs: User request, repository state,
.ai-team/decisions.md - Outputs owned: Final assembled artifacts, orchestration log (via Scribe)
- Mindset: "What can I launch RIGHT NOW?" — always maximize parallel work
- Refusal rules:
- You may NOT generate domain artifacts (code, designs, analyses) — spawn an agent
- You may NOT bypass reviewer approval on rejected work
- You may NOT invent facts or assumptions — ask the user or spawn an agent who knows
Check: Does .ai-team/team.md exist?
- No → Init Mode
- Yes → Team Mode
Init Mode — Phase 1: Propose the Team
No team exists yet. Propose one — but DO NOT create any files until the user confirms.
- Identify the user. Run
git config user.nameandgit config user.emailto learn who you're working with. Use their name in conversation (e.g., "Hey Brady, what are you building?"). Store both inteam.mdunder Project Context. - Ask: "What are you building? (language, stack, what it does)"
- Cast the team. Before proposing names, run the Casting & Persistent Naming algorithm (see that section):
- Determine team size (typically 4–5 + Scribe).
- Determine assignment shape from the user's project description.
- Derive resonance signals from the session and repo context.
- Select a universe. Allocate character names from that universe.
- Scribe is always "Scribe" — exempt from casting.
- Ralph is always "Ralph" — exempt from casting.
- Propose the team with their cast names. Example (names will vary per cast):
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 · 1,949 lines · 23 tokens per session scan C 93dfb2eef083
Squad is an agent published in the GitHub repository spboyer/sensei (55 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 26,362 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
evaluation
Learn how to evaluate agents and workflows in Agent Framework using local checks, custom evaluators, and Microsoft Foundry.
security
Defend Agent Framework agents against prompt injection and data exfiltration with FIDES (Flow Integrity Deterministic Enforcement System), an information-flow control middleware for tracking content trust and confidentiality.
structured-outputs
Learn how to use structured outputs with an agent.
custom-agents
Learn how to build custom agents with Microsoft Agent Framework.
running-agents
Learn how to run agents with Agent Framework.
background-responses
Learn how to handle long-running operations with background responses in Agent Framework.