RAD_framework: Skill for Claude Code

.agents/skills/kickoff/SKILL.md

kickoff is a skill for Claude Code, Codex from seanrreid/RAD_framework. It costs 63 tokens per session (1,161 once invoked), scanned A, original, MIT.

A session-start checklist for RAD projects that reads project instructions, checks Git status, reviews active plans, and asks what to work on.

In plain words
What is it for?
Use it at the start of a work session to read CLAUDE.md, check whether work is on the protected default branch, report plan status, and optionally triage open issues.
Why use it?
It gives the agent the project context and exposes branch, uncommitted-change, or unfinished-plan issues before coding begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code and Codex how to work on RAD_framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RAD_framework configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node harness/cli.js config get roles.architect # also roles.developers, roles.designers.

Reuse

Borrowing it

Nothing to install: this file belongs to seanrreid/RAD_framework. 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/seanrreid/RAD_framework/main/.agents/skills/kickoff/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

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.

agentmods badge for kickoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/seanrreid/rad_framework/kickoff/github.svg)](https://agentmods.dev/skills/seanrreid/rad_framework/kickoff)
Your own site
<a href="https://agentmods.dev/skills/seanrreid/rad_framework/kickoff"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/kickoff/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.

agentmods 80×15 button for kickoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/seanrreid/rad_framework/kickoff"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/kickoff.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 1,161 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01161
Opus 5.5 $0.00025 $0.00464
Sonnet 5.5 $0.00013 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 20d ago against content hash 8e2d2f6e19a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kickoff 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 20d 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/kickoff/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Kickoff

Orient quickly at the start of a session: load project context, check git state, surface what needs attention, and pick a focus. Keep the briefing under ~400 words.

Steps

1. Load project context

Read AGENTS.md for project conventions (or CLAUDE.md if the project has no AGENTS.md) — project description, stack, and conventions. This is the contract for the session. Read role assignments from .rad/config.yml:

node harness/cli.js config get roles.architect   # also roles.developers, roles.designers

2. Check git state

git branch --show-current
git status --short
git log --oneline @{u}.. 2>/dev/null || true

Report the current branch, any uncommitted changes, and how far ahead/behind the remote you are.

Branch guard. Resolve the default branch and warn if you're on it — RAD work happens on rad/ branches, never directly on the protected default branch:

BASE=$(scripts/get-default-branch.sh)

⚠️ You're on {BASE}. RAD work belongs on a rad/[feature] branch.

  • New work: /rad-plan "<feature>" cuts the branch for you.
  • Resuming: node harness/cli.js checkout <feature>.

Stop the briefing on this warning until it's resolved.

3. Report active plans

scripts/rad-status.sh

Dormant runs first. If the output has a ── Dormant Runs (needs a decision) ── section, report it ABOVE every plan-status group — a dormant run is a deliver that is parked awaiting a human decision, and nothing moves until someone makes it. For each entry, give the feature, what it stopped on (reason and wave), the decision it is asking for, and the resume hint exactly as printed: rad deliver <feature> --resume --context "<what you decided>". The section is absent when nothing is parked — then say nothing about dormant runs. A warning: stop-status <feature>: … line means that feature's event log could not be read; mention it so it gets looked at.

Read the full file on GitHub · 121 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.

  1. 20d ago Changed · -3 lines 8e2d2f6e19a1
  2. 23d ago Changed · +1 lines · +5 tokens per session adec2fa24f7b
  3. 27d ago Changed · +4 lines 1f74bf7e5640
  4. 1mo ago Changed · +10 lines b700f7dffc02
  5. 1mo ago Changed · +4 lines fe029bf7488a
  6. 2mo ago First seen · 105 lines · 58 tokens per session scan A 3ebce61efd9a

Subscribe to this mod's changes

kickoff is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,161 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 2026-08-31.