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/zendev-sh/zenflow/claude-mdgit clone --depth 1 https://github.com/zendev-sh/zenflowWrote 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/zendev-sh/zenflow/claude-md)<a href="https://agentmods.dev/instructions/zendev-sh/zenflow/claude-md"><img src="https://agentmods.dev/badge/instructions/zendev-sh/zenflow/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 | $0.01980 | $0.01980 |
| Opus 5 | $0.00990 | $0.00990 |
| Sonnet 5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
zenflow 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.
This is a copy
100% identical to zenflow AGENTS.md — 2 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - zenflow
Instructions for AI contributors working on the zenflow codebase.
Commands
go build ./... # Build library
go build ./cmd/zenflow/ # Build CLI
go test ./... # Test all packages
go test -cover ./... # Test with coverage
golangci-lint run # Lint
./scripts/smoke-examples.sh # Vet + build all 18 embedding examples
go test -tags e2e ./... # Real-LLM integration tests (needs API keys)
Architecture
zenflow is a declarative multi-agent workflow engine for Go. Workflows are YAML; the engine is a DAG executor with an LLM coordinator that narrates progress and routes events through hub-and-spoke mailboxes. The Go SDK layer is goai - any provider goai supports works as a zenflow agent backend.
zenflow/
├── doc.go # Package zenflow doc.
├── interfaces.go # Storage/Tracer/StepIsolation/ApprovalHandler aliases (root facade)
├── workflow.go # Workflow / Step / StepResult / WorkflowResult / Run aliases (root facade)
├── duration.go # Duration alias + FormatDuration / ParseDurationStrict re-exports
├── router_facade.go # Re-exports for internal/router/ public API
├── transcript_facade.go # Re-exports for internal/resume/ public API
├── coord_facade.go # Re-exports for internal/coord/ tool factories
├── agent_facade.go # Re-exports for internal/exec/ AgentRunner ecosystem (AgentRunner, AgentResult, 22 WithRunner*, AgentHandle, sentinels)
├── orchestrator_facade.go # Re-exports for internal/exec/ Orchestrator + 49 With* + Executor + Storage backends + parsers + coord factory + JSON coordinator + ~60 utility symbols
├── internal/
│ ├── types/ # Event, EventType, MessageKind, Output, ProgressSink, PermissionHandler/Request (leaf, no deps on root)
│ ├── spec/ # Workflow / Step / Run / StepResult / AgentConfig / Duration types + Storage / Tracer / StepIsolation / ApprovalHandler / ModelResolver interface contracts + parser & validator helpers
│ ├── router/ # MessageRouter, MailboxStore, deliveryEngine (race-safe send/wake)
│ ├── resume/ # TranscriptStore, InMemoryTranscriptStore
│ ├── coord/ # RunnerHandle interface + 4 coord goai.Tool factories (forward_to_agent, send_message, narrate, finalize)
│ └── exec/ # AgentRunner + Executor + Orchestrator + JSON coordinator + RunFlow/RunGoal/RunAgent + ResumeFlow + 49 With* options + Storage backends (MemoryStorage, FileStorage) + SharedMemory + parsers + validators + scheduler + CEL evaluator + portability lints + isolation default + lifecycle + prompt assembly + 16 source files moved from root
├── cmd/zenflow/
│ ├── main.go # CLI entrypoint
│ ├── flags.go # Shared flag parser
│ ├── cmd_*.go # Subcommand handlers (flow, goal, agent, validate, plan)
│ ├── orchestrator_opts.go # Build orchestrator from CLI flags
│ ├── provider.go # Provider resolver
│ ├── thinking.go # --thinking flag
│ ├── trace_otel.go # --trace flag
│ ├── signals.go # Signal handling
│ ├── workdir.go # Working directory helper
│ ├── permission.go # Interactive permission gate
│ ├── stdout_sink.go # CLI human-readable sink
│ ├── color.go # ANSI color helpers (auto-detect TTY)
│ ├── dag/ # DAG plan helpers
│ └── tool/ # CLI-only IO tools (bash/read/write/glob/grep)
├── sink/
│ ├── json.go # NDJSON event stream
│ ├── buffered.go # ClosableProgressSink wrapping any sink with bounded queue
│ └── lifecycle.go # Sink lifecycle helpers (graceful shutdown / Close())
├── examples/ # 18 //go:build example mains
└── spec/v1/
├── schema.json # JSON Schema (workflow validation)
├── spec.md # Authoritative YAML specification
├── examples/ # 20 reference workflows
└── testcases/ # Conformance fixtures
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 · 142 lines · 1,980 tokens per session scan A c6859e94c01e
zenflow CLAUDE.md is an instructions file published in the GitHub repository zendev-sh/zenflow (49 stars, last pushed today), licensed Apache-2.0. It adds 1,980 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to zenflow AGENTS.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
taskflow AGENTS.md
AGENTS.md instructions for heggria/taskflow, covering agents.md, project overview, architecture, key concepts and phase types (12 total).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).