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/d6t/d6tflow/claude-mdgit clone --depth 1 https://github.com/d6t/d6tflowWrote 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/d6t/d6tflow/claude-md)<a href="https://agentmods.dev/instructions/d6t/d6tflow/claude-md"><img src="https://agentmods.dev/badge/instructions/d6t/d6tflow/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 | $0.03950 | $0.03950 |
| Opus 5 | $0.01975 | $0.01975 |
| Sonnet 5 | $0.00790 | $0.00790 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
d6tflow 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for working in the d6tflow repo.
What this is
d6tflow is a small, self-contained Python library for building data-science workflows: you
declare Task classes with parameters, dependencies (requires), and a run() that
save()s output; the engine runs the DAG in dependency order and skips tasks whose output
already exists. It has no heavyweight workflow-engine dependency — the task model, parameters,
and executor all live in d6tflow/core.py + d6tflow/parameter.py.
Layout
d6tflow/
__init__.py # public API: run, preview, Workflow, WorkflowMulti, FlowExport/Import,
# invalidate_*, requires/inherits, re-exported Parameter types
core.py # the engine: Task, Register metaclass, Target/LocalTarget, flatten,
# getpaths, task_id_str, inherits/requires, find_deps, build()
parameter.py # Parameter, Int/Float/Bool/Date/Dict/List/Enum Parameter
tasks/__init__.py # TaskData (+ TaskCache/Json/Pickle/CSV/Excel/Pq/Markdown...), TaskAggregator
targets/__init__.py# CacheTarget, _LocalPathTarget, DataTarget + format targets, Target re-export
settings.py # global settings (dirpath, cached, check_dependencies, task-id lengths...)
cache.py # `data` = in-memory target cache (dict)
utils.py # print_tree (preview), traverse, param generators, bcolors
functional.py # decorator-based functional Workflow API (uses only d6tflow.requires)
tests/ # pytest suite (see tests/setup.md)
docs/ # examples + docs/todo/ design notes
Ignore bak/, build/, dist/, *.egg-info/, data/, models/, tests-data/ — local
artifacts / backups, not source. (d6tflow/core/ is an empty stale dir; the real module is
d6tflow/core.py.)
Public API (what exists — check here before adding new code)
Everything below is exported from d6tflow (top-level) unless noted. Reach for these
instead of reinventing them.
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.
- 4d ago First seen · 213 lines · 3,950 tokens per session scan A 249363875196
d6tflow CLAUDE.md is an instructions file published in the GitHub repository d6t/d6tflow (947 stars, last pushed 2mo ago), licensed MIT. It adds 3,950 tokens to every session, about $0.0198 per session on Opus 5. 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.