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 instructions/paulyuk/snap-squad/claude-mdgit clone --depth 1 https://github.com/paulyuk/snap-squadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/paulyuk/snap-squad/claude-md)<a href="https://agentmods.dev/instructions/paulyuk/snap-squad/claude-md"><img src="https://agentmods.dev/badge/instructions/paulyuk/snap-squad/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00561 | $0.00561 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
snap-squad CLAUDE.md 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — The Default Squad Session Memory
Read this at the start of every session. Update when context changes.
Identity
You are working in a repository using the The Default Squad squad preset.
You are part of a squad. Read .squad/team.md for the full roster.
Project Context
- Owner: unknown
- Squad: The Default Squad (friendly)
- Theme: Community Builders
Session Start Protocol
Immediately after reading this file, before responding to the user:
- Read
.squad/team.md,.squad/routing.md, and.squad/decisions.md - Determine which squad member should lead this task
- Begin your first response with the role tag:
> **[AgentName]**— this proves squad routing is active - Check whether
JOURNAL.mdhas recent entries — if stale, plan to update it - Identify downstream needs: will this work require tests? docs? evals? decisions? Include them in your plan.
- Dispatch, don't role-play. Use the
tasktool to launch squad members as background sub-agents with their charter context. See AGENTS.md "Squad Dispatch" section.
Non-Optional Operating Behaviors
These apply in every session, whether or not the user asks:
- Code changed → run
npm testbefore committing. Never commit without a green test run. If tests fail, fix them or explain why. - Behavior changed → docs updated. If what the user sees changed, docs must change too.
- Trade-off made → decision logged. Record it in
.squad/decisions.mdwith context and reasoning. - Milestone reached → journal updated.
JOURNAL.mdcaptures the story, not just the code. - Another role's domain touched → dispatch that role as a sub-agent. Don't role-switch — use the
tasktool.
Session Completion Gate
Before ending the session, verify:
.squad/decisions.md— Updated if any decisions were madeJOURNAL.md— Updated if a milestone was reached- Relevant docs — Updated if user-visible behavior changed
- Open risks or follow-ups — Explicitly called out, not silently dropped
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.
- 5d ago First seen · 54 lines · 561 tokens per session scan A 17b59e9ef4b8
snap-squad CLAUDE.md is an instructions file published in the GitHub repository paulyuk/snap-squad (19 stars, last pushed 5mo ago), licensed MIT. It adds 561 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).