A repository-onboarding skill that studies the source code, documentation, and tests, prepares the development environment, runs tests, and writes a short project report. It treats tests as records of expected behaviour.

Use it to map a repository, including packages in a monorepo (a repository containing multiple projects), find entry points, install dependencies, learn how tests run, and summarise the project.

It gives an agent a grounded understanding of an unfamiliar codebase before changes are made. This avoids relying only on guesses from production code or undocumented assumptions.

rpa-init — Skill for Claude Code and Codex by coddy-project

Install

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.

Any agent

npx skills add coddy-project/coddy-agent --skill rpa-init

Clone the repo

git clone --depth 1 https://github.com/coddy-project/coddy-agent

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/coddy-project/coddy-agent/rpa-init/github.svg)](https://agentmods.dev/skills/coddy-project/coddy-agent/rpa-init)

Your own site

<a href="https://agentmods.dev/skills/coddy-project/coddy-agent/rpa-init"><img src="https://agentmods.dev/badge/skills/coddy-project/coddy-agent/rpa-init/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/coddy-project/coddy-agent/rpa-init"><img src="https://agentmods.dev/badge/skills/coddy-project/coddy-agent/rpa-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 685 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	$0.00063	$0.00685
Opus 5.5	$0.00025	$0.00274
Sonnet 5.5	$0.00013	$0.00137
Haiku 4.5	$0.00006	$0.00068

Measured 13d ago against content hash d99c4b3a8bb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rpa-init 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 13d 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.

internal/skills/bundled/rpa-init/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RPA project initialization (context warm-up)

Intent

Treat automated tests as the project long-term memory. Initialization maps documented intent, behavior encoded in tests, and implementation. Prefer learning from tests and docs before inferring only from production code.

Preconditions you must verify yourself

Read application source, docs, and tests (test code is part of the specification).
Dev environment - install dependencies and prepare the environment the repo documents (for example python -m venv .venv, pip install -e ., uv sync, npm ci, or commands from README / CI). If the stack is not Python, follow that ecosystem's norms.
Locate how tests are run. Default for Python: pytest via .venv when present. Respect pytest.ini, pyproject.toml, or tox / nox if present.
Identify entrypoints: README, docs/, package layout, main modules, CLI.

Workflow

Optional git update — if the directory is a git repository and the user has not asked to stay on the current commit, run git pull to refresh the local copy before analysis.
Scan repository structure (layout, monorepo packages if any).
Read user-facing documentation and specs.
Study test code (naming, fixtures, markers, integration vs unit). This is the BDD-facing view of expected behavior.
Set up dev environment so tests can run (create venv, install deps, any documented bootstrap). Note blockers if setup cannot be completed.
Run the test suite, for example:
```
.venv/bin/pytest -q
```
If tests fail, record where and why (do not fix unless the user asked).
Summarize in a concise report (see template). Use English for code-related terms if the codebase uses English; respond in the user's language for narrative.

Report template

Use this structure (adapt if needed):

## Project snapshot
- Purpose (one paragraph)
- Main packages and boundaries

## Dev environment
- What was installed or configured (venv, package manager, key commands)

## How to run tests
- Commands actually used

## Behavior from tests
- Scenarios covered by tests (bullets)
- Gaps (important paths with weak or missing tests)

## Risks and notes
- Flaky tests, secrets, external services

## Suggested next steps
- 1 to 3 follow-ups

Read the full file on GitHub · 72 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago Changed · +1 lines d99c4b3a8bb2
22d ago Changed · +1 lines 0e6b837118d0
1mo ago First seen · 70 lines · 63 tokens per session scan A a399e3eec8f7

Subscribe to this mod's changes

rpa-init is a skill published in the GitHub repository coddy-project/coddy-agent (175 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 685 once invoked, about $0.0003 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 2026-09-16.

LLM Research Testing acp agent-client-protocol cli mcp openai

python-repl

Interactive Python REPL automation with common helpers and best practices.

gptme/gptme · 15 tokens

reproduce

Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed set, reproduced, reproduced within tolerance, partially…

synthetic-sciences/openscience · 116 tokens

tmux-manual-qa

Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.

code-yeongyu/senpi · 66 tokens

rpa-init