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/facets-cloud/flow/claude-mdgit clone --depth 1 https://github.com/Facets-cloud/flowWhat 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 | $0.01791 | $0.01791 |
| Opus 5 | $0.00896 | $0.00896 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade B, and why
flow CLAUDE.md scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `hookCommand` (SessionStart) and `userPromptSubmitHookCommand` (UserPromptSubmit) in `internal/app/skill.go` are the exact strings matched in `~/.claude/settings.json`. Changing either orphans existing installations. How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flow — repo conventions
What this is
A Go CLI (flow) that manages personal tasks and bootstraps per-task Claude Code sessions. SQLite via modernc.org/sqlite (pure Go, no CGO).
Build and test
# Build (produces ./flow in the repo dir, which is on PATH)
make build
# or: go build -o flow .
# Full install (build + PATH + init + skill + hook)
make install
# Run all tests (fast — no network, no real iTerm/Claude)
make test
# or: go test ./...
# Run a single test
go test -run TestE2EFullRoundtrip -v ./internal/app/
Tests use $FLOW_ROOT pointed at a temp directory and override $HOME so nothing touches real ~/.flow/ or ~/.claude/. External dependencies (osascript, claude CLI) are mocked via package-level function vars.
Project structure
flow/
├── main.go # thin entry point — calls app.Run()
├── internal/
│ ├── app/ # CLI commands and dispatch
│ │ ├── app.go # Run(), printUsage()
│ │ ├── helpers.go # flagSet()
│ │ ├── add.go # flow add project|task
│ │ ├── archive.go # flow archive|unarchive
│ │ ├── do.go # flow do — session spawner
│ │ ├── done.go # flow done
│ │ ├── due.go # flow due
│ │ ├── edit.go # flow edit
│ │ ├── hook.go # flow hook session-start
│ │ ├── init.go # flow init, flowRoot(), kbSeeds()
│ │ ├── list.go # flow list tasks|projects
│ │ ├── priority.go # flow priority
│ │ ├── show.go # flow show task|project
│ │ ├── skill.go # flow skill install|uninstall|update
│ │ ├── transcript.go # flow transcript — session jsonl reader
│ │ ├── waiting.go # flow waiting
│ │ ├── workdir.go # flow workdir
│ │ ├── bootstrap.go # UUID gen, session file scanning
│ │ ├── resolve.go # task/project slug resolution
│ │ ├── slug.go # name-to-slug conversion
│ │ ├── skill/SKILL.md # embedded lean skill core (//go:embed skill)
│ │ ├── skill/references/*.md # on-demand workflow references (embedded)
│ │ └── *_test.go
│ ├── flowdb/ # SQLite data layer
│ │ ├── db.go # schema, models, CRUD queries
│ │ └── db_test.go
│ ├── iterm/ # iTerm2 tab spawning
│ │ └── iterm.go
│ ├── terminal/ # macOS Terminal.app tab spawning
│ │ └── terminal.go
│ ├── warp/ # Warp tab spawning (warp:// URI + osascript keystroke)
│ │ └── warp.go
│ ├── zellij/ # zellij tab spawning
│ │ └── zellij.go
│ └── spawner/ # backend selection + dispatch
│ └── spawner.go
├── Makefile
├── README.md
├── CLAUDE.md
├── .gitignore
├── go.mod
└── go.sum
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.
- 2d ago First seen · 117 lines · 1,791 tokens per session scan B 410673cf23a4
flow CLAUDE.md is an instructions file published in the GitHub repository Facets-cloud/flow (100 stars, last pushed 6d ago), licensed MIT. It adds 1,791 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
opencode-claude-memory AGENTS.md
Instructions for kuitos/opencode-claude-memory, covering agents.md, structure, where to look, critical coupling and conventions.
memex AGENTS.md
Instructions for iamtouchskyer/memex, covering memex — agent working instructions, what is this, before you touch anything, how the code is layered and files you'll actually need.
rekal-cli CLAUDE.md
Instructions for rekal-dev/rekal-cli, covering rekal cli, soul, standing rules, architecture and key directories.
stella AGENTS.md
AGENTS.md instructions for macanderson/stella, covering agents.md, essential commands, the gate — what every push is held to, architecture: ports, not direct dependencies and the definition of done: witness tests.
stella CLAUDE.md
Claude Code instructions for macanderson/stella, covering claude.md and hard rules for every session.
lerim AGENTS.md
AGENTS.md instructions for nablo-io/lerim, covering lerim, summary, current architecture, trace format and parsing and how to query existing context.