Borrowing it
Nothing to install: this file belongs to saagpatel/mcpforge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saagpatel/mcpforge/main/.agents/skills/repo-onboarding/SKILL.mdgit clone --depth 1 https://github.com/saagpatel/mcpforgeWrote 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/saagpatel/mcpforge/repo-onboarding)<a href="https://agentmods.dev/skills/saagpatel/mcpforge/repo-onboarding"><img src="https://agentmods.dev/badge/skills/saagpatel/mcpforge/repo-onboarding.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 5.1 | $0.00048 | $0.00835 |
| Opus 5 | $0.00024 | $0.00417 |
| Sonnet 5 | $0.00010 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
repo-onboarding 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-onboarding
Beginner At A Glance
- What this skill does: Gives a fast mental model of how
mcpforgeis laid out and where to look first. - Use this when: Use when starting work in
mcpforge, especially before changing generation, validation, or CLI behavior. - Say it naturally: "Onboard me to mcpforge" | "How is mcpforge structured?" | "Where should I edit this in mcpforge?"
PM Output Style
- Use the big-picture PM update format by default: Project, Goal, Headline, State, Impact, Why it matters, What you need from me, Blockers.
- Keep language beginner-friendly and avoid technical receipts unless explicitly requested.
Skill Contract v2
use_when:
- The current workspace is
~/Projects/mcpforge. - The user asks for onboarding, architecture, safe edit targets, or a quick mental model before changes.
- A request touches generation, validation, CLI behavior, MCP server output, or tests and repo context would reduce risk.
dont_use_when:
- The task is a tiny isolated edit where repo structure is already obvious from the touched file.
trigger_phrases:
- onboard me to mcpforge; explain this repo; where should I change this; how is mcpforge organized
anti_triggers:
- one-line typo only
expected_inputs:
- User goal, touched area if known, and current repo state.
expected_outputs:
- Short repo map, likely edit points, validation path, and top risks.
success_criteria:
- A collaborator can start editing the right files with a clear understanding of how to verify the change.
companion_skills:
- mcp-debugger,promptfoo-eval-loop,quality-gatekeeper
risk_class: low
default_chain_role: primary
Repo Map
README.md: product promise, CLI surface, and supported workflows.pyproject.toml: package metadata, dependencies, scripts, and test/lint defaults.src/: primary implementation. Start here for CLI, planning, generation, validation, and MCP server code.tests/: regression surface. Prefer adding or updating tests when behavior changes.examples/: useful for understanding generated output and intended use patterns.HANDOFF.mdandIMPLEMENTATION-ROADMAP.md: good context when the task is roadmap-shaped rather than purely local.
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.
- 6d ago First seen · 81 lines · 48 tokens per session scan A 30c308bb7a44
repo-onboarding is a skill published in the GitHub repository saagpatel/mcpforge (0 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 835 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.