What is repo-onboarding?

A guide for getting familiar with the mcpforge codebase before making changes. It explains the project layout, how its generation and checks work, and where edits are safest.

Use it when onboarding to mcpforge or deciding where to change generation, validation, command-line behavior, server output, or tests.

It reduces the time spent searching through an unfamiliar repository and lowers the risk of changing the wrong part.

How saagpatel/mcpforge configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/saagpatel/mcpforge/main/.agents/skills/repo-onboarding/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/saagpatel/mcpforge

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/saagpatel/mcpforge/repo-onboarding/github.svg)](https://agentmods.dev/skills/saagpatel/mcpforge/repo-onboarding)

Your own site

<a href="https://agentmods.dev/skills/saagpatel/mcpforge/repo-onboarding"><img src="https://agentmods.dev/badge/skills/saagpatel/mcpforge/repo-onboarding/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/saagpatel/mcpforge/repo-onboarding"><img src="https://agentmods.dev/badge/skills/saagpatel/mcpforge/repo-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 834 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00045	$0.00834
Opus 5.5	$0.00018	$0.00334
Sonnet 5.5	$0.00009	$0.00167
Haiku 4.5	$0.00005	$0.00083

Measured 1mo ago against content hash f499a64629ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.agents/skills/repo-onboarding/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 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 mcpforge is 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 detected Git root is an MCP Forge checkout, regardless of its local or Cloud path.
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.md and IMPLEMENTATION-ROADMAP.md: good context when the task is roadmap-shaped rather than purely local.

Read the full file on GitHub · 80 lines

Changes

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.

1mo ago Changed · -1 lines · -3 tokens per session f499a64629ae
2mo ago First seen · 81 lines · 48 tokens per session scan A 30c308bb7a44

Subscribe to this mod's changes

repo-onboarding is a skill published in the GitHub repository saagpatel/mcpforge (0 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 834 once invoked, about $0.0002 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.

Code Generation Python ai-tools cli fastmcp mcp

repo-onboarding next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-onboardingsaagpatel/mcpforge	Skill	0	3d ago	MIT	A	45	Claude Code, Codex
dd-code-generationDataDog/pup	Skill	1.0k	yesterday	Apache-2.0	A	16	Claude Code
python-backendWrongStack/WrongStack	Skill	404	yesterday	MIT	A	93	Claude Code, Codex
gurume-clinarumiruna/gurume	Skill	13	8d ago	MIT	A	127	Claude Code, Codex
code-review-pythonsoulcodex/agentic	Skill	10	7d ago	MIT	A	59	Claude Code, Codex
lint-mdsergeiwallace/ai-cli-utils	Skill	2	today	MIT	A	20	Claude Code
pypiJustVugg/tools-factory	Skill	62	4mo ago	MIT	A	37	Claude Code, Codex

mcpforge: Skill for Claude Code