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/strait-dev/strait/claude-mdgit clone --depth 1 https://github.com/strait-dev/straitWhat 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 | $0.05821 | $0.05821 |
| Opus 5 | $0.02910 | $0.02910 |
| Sonnet 5 | $0.01164 | $0.01164 |
| Haiku 4.5 | $0.00582 | $0.00582 |
Grade A, and why
strait 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 yesterday.
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.
This is a copy
100% identical to strait AGENTS.md — 0 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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor Operating Guide
Operating guide for contributors and AI agents working on this repository. Read this before making changes.
If instructions conflict, use this priority order:
- Direct user request
- This file
- Existing code patterns
- Personal preference
The same guide lives in both AGENTS.md and CLAUDE.md. Keep them in sync: any edit to one must be mirrored in the other.
1. What Strait is
Strait is a job orchestration and workflow platform shipped as a single Go binary. PostgreSQL is the source of truth. Strait's internal queue uses a vendored and modified SQL snapshot of PgQue as the ready-event log, while Strait owns run state, execution ownership, retries, workflows, workers, observability, and APIs. Redis powers pub/sub and SSE. Strait does not run user code itself: job code lives on the customer's infrastructure and is reached either through an HTTP endpoint Strait POSTs to, or through a long-lived worker process that connects to the API over gRPC and streams runs back. The binary runs in api, worker, or all mode. The two editions (community and cloud) are selected at compile time through Go build tags.
Read first:
README.mdapps/docs/introduction.mdx: feature overviewapps/docs/quickstart.mdx: first setupapps/docs/architecture.mdx: internals and design rationaleSELFHOST.md: self-hosted deployment
2. Tech stack
- Language: Go 1.26.4, module
strait, in a Bun + Turbo monorepo - HTTP:
go-chi/chi/v5withdanielgtaylor/huma/v2(OpenAPI generation) - Database: PostgreSQL through
jackc/pgx/v5, no ORM. Migrations are embedded SQL. - Cache and pub-sub:
redis/go-redis/v9,eko/gocache,maypok86/otter - Concurrency:
sourcegraph/conc,alitto/pond/v2,failsafe-gofor retries and circuit breakers - Worker plane (gRPC):
google.golang.org/grpcwithprotobuffor bidirectional streaming between the API and connected workers - Analytics (optional):
ClickHouse/clickhouse-go/v2 - Monitoring: OpenTelemetry, Prometheus, Pyroscope, Sentry
- Helpers:
samber/lo,samber/oops,samber/slog-multi - CLI internals:
spf13/cobra(the user-facing CLI lives in strait-dev/cli) - JWT:
golang-jwt/jwt/v5 - Cloud-only billing:
stripe/stripe-go/v82 - Tests:
testcontainers-gofor real Postgres and Redis in integration tests - Tooling: golangci-lint, lefthook, Biome, govulncheck, gitleaks, buf, zizmor
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.
- yesterday First seen · 452 lines · 5,821 tokens per session scan A c6256d6099a1
strait CLAUDE.md is an instructions file published in the GitHub repository strait-dev/strait (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,821 tokens to every session, about $0.0291 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to strait AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
ollama CLAUDE.md
Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.
autospec AGENTS.md
Instructions for ariel-frischer/autospec, covering agents.md, prerequisites, commands, build & dev and single test.