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/soapbucket/sbproxy/claude-mdgit clone --depth 1 https://github.com/soapbucket/sbproxyWhat 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 | $0.10201 | $0.10201 |
| Opus 5 | $0.05101 | $0.05101 |
| Sonnet 5 | $0.02040 | $0.02040 |
| Haiku 4.5 | $0.01020 | $0.01020 |
Grade A, and why
sbproxy CLAUDE.md scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
conformance/ - vendored curl-and-bash conformance suite This is a copy
88% identical to sbproxy AGENTS.md — 116 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 814 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sbproxy (Rust workspace)
Last modified: 2026-08-28
The active implementation of sbproxy. Cargo workspace with ~20
crates under crates/, an e2e suite under e2e/, examples under
examples/, and an internal observability/cache/AI/security stack.
Pre-commit checks
Before committing any change, run all checks. Each one corresponds to a
required CI gate; if any fails locally, CI will fail too. The table is
ordered the way scripts/check.sh runs them, cheapest first, so a
failure that takes seconds to find is not discovered behind a
ten-minute build.
| Check | Command |
|---|---|
| Tracker placeholders | grep -rn 'WOR-XXX' crates/ --include='*.rs' --include='*.toml' (any hit fails) |
| pub-item ratchet | bash scripts/check-pub-item-ratchet.sh |
| unwrap/expect/panic ratchet | bash scripts/check-unwrap-ratchet.sh |
| Operator URLs at log lines | bash scripts/check-log-url-ratchet.sh |
| AI dispatch stack budget | bash scripts/check-stack-budget-ratchet.sh |
| Attribute placement | python3 scripts/check-attribute-placement.py --check |
| Attribute theft (diff-scoped) | python3 scripts/check-attribute-theft.py --check |
| Spec citations | bash scripts/check-spec-citations.sh |
| Env mutation | bash scripts/check-env-mutation.sh |
| Durable file modes | bash scripts/check-durable-file-modes.sh |
| Secret-bearing Debug registry | bash scripts/check-secret-debug-registry.sh |
| NOTICE (Apache-2.0-only) | bash scripts/check-notice.sh |
| Doc drift | bash scripts/check-doc-drift.sh |
| Tapes + GIF wiring | make tapes-check |
| Doc configs | python3 scripts/sync-doc-configs.py --check |
| Documented output | python3 scripts/check-doc-captures.py --check --stackless-only |
| Review-evidence parser | python3 scripts/check-review-evidence.py --self-test |
| Changelog fragments | python3 scripts/changelog-fragments.py --check |
| Installer | sh scripts/tests/install_verify.sh |
| Format | cargo fmt --all -- --check |
| Nested lockfiles | bash scripts/check-nested-lockfiles.sh |
| Supply chain (crates) | cargo deny --all-features check |
| Supply chain (npm) | cd ui && npm audit --package-lock-only --audit-level=high |
| UI | cd ui && npm ci && npm run typecheck && npm run test -- --run |
| Build | cargo build --workspace --exclude sbproxy-e2e --locked |
| Test | cargo nextest run --workspace --exclude sbproxy-e2e --locked --profile ci |
| Doctest | cargo test --workspace --exclude sbproxy-e2e --locked --doc |
| Clippy | cargo clippy --workspace --all-targets -- -D warnings |
| Docs | RUSTDOCFLAGS="-D warnings -D missing_docs" cargo doc --workspace --no-deps --locked |
| Payment features (on by default) | bash scripts/check.sh; SBPROXY_CHECK_PAYMENTS=0 skips it |
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.
- 3d ago First seen · 814 lines · 10,201 tokens per session scan A c3631cb7790c
sbproxy CLAUDE.md is an instructions file published in the GitHub repository soapbucket/sbproxy (51 stars, last pushed 3d ago), licensed Apache-2.0. It adds 10,201 tokens to every session, about $0.0510 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 88% identical to sbproxy AGENTS.md, differing in 116 lines, and is treated as a copy.
Other instructions, from other repositories
deltallm AGENTS.md
Instructions for deltawi/deltallm, covering repository instructions, required first step and precedence and maintenance.
higress AGENTS.md
AGENTS.md instructions for higress-group/higress, covering agents.md, mandatory issue-spec gate for agent-assisted changes, repository layout, plugins and plugins/wasm-go/ (primary wasm plugin framework, go).
ai-gateway AGENTS.md
Instructions for ferro-labs/ai-gateway, covering agents.md, project overview, current development snapshot, public-facing wording and build, test, and run commands.
litellm AGENTS.md
AGENTS.md instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].
litellm GEMINI.md
Gemini CLI instructions for BerriAI/litellm, a project described as: The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM].
tiygate AGENTS.md
Instructions for tiylabs/tiygate, covering repository guidelines, project structure & module organization, engineering principles, build, test, and development commands and coding style & naming conventions.