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 agentmods add skills/seanrreid/rad_framework/kickoffnpx skills add seanrreid/RAD_framework --skill kickoffgit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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/seanrreid/rad_framework/kickoff)<a href="https://agentmods.dev/skills/seanrreid/rad_framework/kickoff"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/kickoff.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 | $0.00058 | $0.00854 |
| Opus 5 | $0.00029 | $0.00427 |
| Sonnet 5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
kickoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Kickoff
Orient quickly at the start of a session: load project context, check git state, surface what needs attention, and pick a focus. Keep the briefing under ~400 words.
Steps
1. Load project context
Read CLAUDE.md — project description, stack, conventions, role assignments, and
the Agent Scope Map. This is the contract for the session.
2. Check git state
git branch --show-current
git status --short
git log --oneline @{u}.. 2>/dev/null || true
Report the current branch, any uncommitted changes, and how far ahead/behind the remote you are.
Branch guard. Resolve the default branch and warn if you're on it — RAD work
happens on rad/ branches, never directly on the protected default branch:
BASE=$(scripts/get-default-branch.sh)
⚠️ You're on
{BASE}. RAD work belongs on arad/[feature]branch.
- New work:
/rad-plan "<feature>"cuts the branch for you.- Resuming:
git fetch && git checkout rad/<feature>.
Stop the briefing on this warning until it's resolved.
3. Report active plans
scripts/rad-status.sh
Group what it returns by status and surface the actionable ones first:
- pending-review → Awaiting architect approval — the architect runs
/rad-approve <feature>. - approved → Ready to execute —
/rad-deliver .agents/plans/<feature>.md. - in-progress → Delivery underway — note the
rad/branch.
Skip silently if there are no plans.
Auto-clear count. The severity-routed approval gate records each policy
auto-clear as an approved event with recordedBy === 'policy' in the per-feature
audit logs. Count them across the feature event logs and surface one line —
Auto-cleared: N changes since last session — in the report below. Skip silently
if the count is zero or no event logs exist.
jq -r 'select(.type=="approved" and .recordedBy=="policy")' \
.agents/state/*/events.jsonl 2>/dev/null | jq -s 'length'
4. (Optional) Triage open issues
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.
- 4d ago First seen · 105 lines · 58 tokens per session scan A 3ebce61efd9a
kickoff is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 854 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…