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/pipefy/ai-toolkit/agents-mdgit clone --depth 1 https://github.com/pipefy/ai-toolkitWhat 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 | $0.03184 | $0.03184 |
| Opus 5 | $0.01592 | $0.01592 |
| Sonnet 5 | $0.00637 | $0.00637 |
| Haiku 4.5 | $0.00318 | $0.00318 |
Grade A, and why
ai-toolkit AGENTS.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 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.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Documentation map
README.md— Project pitch, one-page install front door (README.md#installation: hosted MCP, Quick install, Claude Code plugin, CLI, skills), repo layout, MCP tools table, contributing.CONTRIBUTING.md— Skills contribution guide (frontmatter, CI, style); entry point for GitHub contributors.docs/README.md— Index of docs by surface (MCP, CLI, SDK) and shared guides.docs/config.md—PIPEFY_*environment variables,config.tomlschema, precedence chain.docs/parity.md— MCP tool ↔ CLI command parity matrix. Source of truth for coverage and deferrals.docs/MIGRATION.md— What existing MCP users need to know about v0.1.docs/dependencies.md— Rationale for runtime dependencies.docs/uninstall.md—uninstall.sh --scanand teardown, and switching between the hosted, local, and plugin channels. The two root scripts are colocated soinstall.shanduninstall.shstay reviewable side by side; a test asserts every file the installer writes is one the teardown accounts for.docs/architecture.md: Intra-package layering (domain, adapter, composition root), type ownership at boundaries, ports, and the alternative-constructor guide.docs/mcp/tools/— Per-area MCP tool reference (parameters, edge cases, cross-cutting behavior). Includesidentifiers.md, the canonical map of which tool/argument expects slug vsinternal_idvs uuid vs numeric id.docs/cli/— CLI-specific guides (e.g. introspect-then-execute).docs/sdk/README.md— Usingpipefyas a library.skills/AGENTS.md— Skill-authoring guide (frontmatter, naming, style). Start here before adding a skill.skills/onboarding/pipefy-toolkit-setup/— First-time setup checklist for agents (links to README snippets; does not own commands).
Project structure
packages/sdk/ → pipefy (Vendor API SDK — GraphQL, models, services; dist named `pipefy`, import module `pipefy_sdk`)
packages/mcp/ → pipefy-mcp-server (MCP tools, server lifecycle; depends on pipefy)
packages/cli/ → pipefy-cli (Typer CLI; depends on pipefy)
skills/ → agent skills catalog (Markdown; no Python package)
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 · 157 lines · 3,184 tokens per session scan A 6cdc0aa4f213
ai-toolkit AGENTS.md is an instructions file published in the GitHub repository pipefy/ai-toolkit (44 stars, last pushed 6d ago), licensed Apache-2.0. It adds 3,184 tokens to every session, about $0.0159 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
notebooklm-py CLAUDE.md
Instructions for teng-lin/notebooklm-py, covering claude.md, project overview, development commands, full guide: docs/installation.md and before pushing.
notebooklm-py AGENTS.md
Instructions for teng-lin/notebooklm-py, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.