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 skills add ecorkran/context-forge --skill cf-onboardgit clone --depth 1 https://github.com/ecorkran/context-forgeWrote 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/skills/ecorkran/context-forge/cf-onboard)<a href="https://agentmods.dev/skills/ecorkran/context-forge/cf-onboard"><img src="https://agentmods.dev/badge/skills/ecorkran/context-forge/cf-onboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ecorkran/context-forge/cf-onboard"><img src="https://agentmods.dev/badge/skills/ecorkran/context-forge/cf-onboard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00609 |
| Opus 5.5 | $0.00014 | $0.00244 |
| Sonnet 5.5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
cf-onboard 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Forge Onboard
You are guiding a user through Context Forge project onboarding. Follow these steps in order — skip any step whose precondition is already met.
Step 1 — Detect existing project
Check whether a Context Forge project is already registered at the current working directory.
Run cf project list and check the output.
- If a project exists at this path → skip to Step 3.
- If no project exists → continue to Step 2.
Step 2 — Set up the project
Ask the user what they'd like to name their project. If they provided a name with the request, use that. If the user declines to choose, use the current directory name.
Run cf init --name <name>. This single command handles
everything: git initialization, project registration, guide installation,
command installation, and IDE setup.
Important: Do not rely on environment context (like "Is a git repository")
to determine git status — cf init checks the actual directory and handles
git initialization itself.
If the Context Forge MCP server is configured and shell access is unavailable, fall back to its tools:
- Call
project_createwithnameandprojectPath(the CWD). - Call
guide_installto install the AI Project Guide. Note: the MCP fallback cannot initialize git. If the directory is not a git repository, inform the user they need to rungit initfirst.
Step 3 — Check the codebase
Judge the current directory before starting any concept conversation.
Run cf detect --json.
The result is a JSON report with an outcome, or an error object with an error field.
- If
outcomeisbrownfieldoradoption-incomplete→ print each entry ofnoticesexactly as given, then stop. Do not build the context prompt and do not start a concept conversation. - If the result is an error object → show its
messageand stop. - Otherwise → continue to Step 4.
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.
- yesterday Changed · +12 lines 848b72588f00
- 5d ago Changed · -9 lines f7b977eebb5b
- 11d ago Changed · +5 lines c6ce95201b93
- 1mo ago First seen · 62 lines · 36 tokens per session scan A b3e6b7bd4c4d
cf-onboard is a skill published in the GitHub repository ecorkran/context-forge (5 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 609 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). For AI agents (conversational), see pipefy-ai-agents.
pipefy-pipes-and-cards
Use this skill when the user wants to read, create, update, or delete pipes, phases, phase fields, labels, cards, comments, or field conditions. Use the seed-pipe-across-phases workflow when populating empty phases for demos or QA.
pipefy-portal-setup
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Uses Interfaces and internalapi. Not for pipes/cards, and not for HTML interfaces (use pipefy-html-interfaces).
pipefy-process-impact
Use this skill when the user asks whether an automation or AI agent would pay off, where to start automating a process, how much time a change gives back, or for a short internal justification. Answers from the conversation first; when the user names a pipe, reads what already runs there before pointing at a step. Not…
pipefy-process-intelligence
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…
pipefy-process-design
Use this skill ONLY when the user explicitly asks for help designing or architecting a process ("help me design", "what's the best structure", "how do I organize this flow?"). For direct execution requests ("create a pipe for X", "build a reimbursement process", or any message with a detailed spec), skip this skill…