CLAUDE

CLAUDE is an agent for coding agents from TesslateAI/OpenSail. It costs 0 tokens per session (340 once invoked), scanned A, original, Apache-2.0.

A set of unit tests for a multi-agent orchestration system, where software coordinates several AI agents. The tests use a temporary SQLite database, a small file-based database, and the real asynchronous service layer.

In plain words
What is it for?
Use it to test unique task assignment under concurrent workers, budget exhaustion and fallbacks, and tools that require approval before an agent can proceed.
Why use it?
It checks that task allocation, usage limits, and approval rules behave correctly together with the production database schema.

Agent

Install

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.

agentmods
npx agentmods add agents/tesslateai/opensail/claude
Clone the repo
git clone --depth 1 https://github.com/TesslateAI/OpenSail

Wrote 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.

agentmods badge for CLAUDE

README.md
[![agentmods](https://agentmods.dev/badge/agents/tesslateai/opensail/claude.svg)](https://agentmods.dev/agents/tesslateai/opensail/claude)
Your own site
<a href="https://agentmods.dev/agents/tesslateai/opensail/claude"><img src="https://agentmods.dev/badge/agents/tesslateai/opensail/claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00340
Opus 5 $0.00000 $0.00170
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured 3d ago against content hash 39597c839073, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CLAUDE 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 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.

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.

orchestrator/tests/agents/CLAUDE.md · 36 lines

What it actually says

tests/agents

Purpose

Unit coverage for the multi-agent orchestration skeleton:

  • ticket allocator (app/services/agent_tickets.py)
  • budget interceptor (app/services/agent_budget.py)
  • approval gate (app/services/agent_approval.py)

Each test migrates a throwaway SQLite file to head so the schema matches what ships in production, then exercises the services via a real AsyncSession.

Key files

  • conftest.pysqlite_url, async_session, session_factory fixtures + a make_project_id helper. SQLite FKs are off by default, which lets tests insert agent_tasks rows without seeding the full projects / users graph.
  • test_ticket_allocator.py — ref_id monotonicity + concurrent checkout disjointness (10 workers over 10 queued tickets).
  • test_budget.py — unlimited fallback, exhaustion blocking, agent-wide fallback, safe-degrade contract.
  • test_approval.py — gated tool raises ApprovalRequired and flips status; approve flips back to queued.
  • orchestrator/app/services/agent_tickets.py
  • orchestrator/app/services/agent_budget.py
  • orchestrator/app/services/agent_approval.py
  • tests/migrations/test_0050_orchestration.py — schema-level checks.

When to load

Load when touching anything in the orchestration skeleton (ticket lifecycle, budget math, approval gating) or when extending the allocator to wire into the worker claim path.

Changes

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.

  1. 3d ago First seen · 36 lines · 0 tokens per session scan A 39597c839073

Subscribe to this mod's changes

CLAUDE is an agent published in the GitHub repository TesslateAI/OpenSail (636 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 340 tokens. 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.

Related

Other agents, from other repositories

tdd-guide

Red-Green-Refactor TDD 사이클 강제. 테스트 먼저 작성 → 최소 코드 구현 → 리팩토링. 커버리지 80%+ 엣지 케이스 분석 포함. Use proactively when 새 기능 구현, 버그 수정, 리팩토링을 시작할 때 — 특히 "TDD로", "테스트 먼저", "테스트 작성"이 포함된 요청. 빌드 에러 수정은 build-error-resolver, E2E는 e2e-runner 사용.

sangrokjung/claude-forge · 110 tokens

deployment-manager

Deployment specialist: production releases, rollback procedures, feature flags, blue-green/zero-downtime deployments.

yonatangross/orchestkit · 24 tokens

tester

Test writing and execution. Runs tests, analyzes coverage, writes missing tests. DELEGATE when user asks: "Write tests for X" / "Add test coverage" / "Test this component" "Run the tests" / "Check if tests pass" / "Run E2E tests" "What's the test coverage?" / "Find untested code" After implementation to verify…

darkroomengineering/cc-settings · 106 tokens

TOOL_PARSE_CORPUS

The behavioral corpus for the text tool-call parser, migrated from 4900 lines of Rust unit tests into executable conformance fixtures for the harn#5142 parse re-platform. Every baseline was generated from the observed stdout of the built binary, never from reasoning and never from the Rust assertions, so the corpus…

burin-labs/harn · 0 tokens

test-engineer

Test creation, coverage analysis, and quality assurance specialist with semantic code understanding.

stefan-jansen/claude-code-toolkit · 18 tokens

qa-tester

Creates and runs test suites. Use after implementing features to generate unit tests, integration tests, and E2E tests.

faizkhairi/claude-code-blueprint · 28 tokens