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.
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/commands/team/rad-deliver.mdgit 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/commands/seanrreid/rad_framework/rad-deliver)<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-deliver"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-deliver.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 | $0.00080 | $0.03167 |
| Opus 5 | $0.00040 | $0.01584 |
| Sonnet 5 | $0.00016 | $0.00633 |
| Haiku 4.5 | $0.00008 | $0.00317 |
Grade A, and why
rad-deliver 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rad-deliver
Execute an approved plan wave by wave. Each wave is delegated to a sub-agent with only the files it needs. Main context stays lean — it orchestrates and logs, never accumulates task implementation detail.
Under the Lane B model the work has lived on its rad/[feature] branch since
/rad-plan — that branch carries the plan, the approval, and now the code. There
is no separate deliver branch, and the deliver PR is the only PR.
Input
$ARGUMENTS must be the path to a plan file:
/rad-deliver .agents/plans/email-confirmation.md
If empty, list available approved plans (reading branch tips):
scripts/rad-status.sh 2>/dev/null | grep approved || echo "No approved plans found."
Process
Step 1: Resolve and validate the work branch
Read the plan file's Branch: header and validate it. Never cut a new branch — a
plan missing the Branch: field (or carrying an old plan//deliver/ name) was
created before the Lane B workflow:
PLAN_FILE="$ARGUMENTS"
WORK_BRANCH=$(grep -E '^Branch:' "$PLAN_FILE" | head -1 | awk '{print $2}')
if [[ ! "$WORK_BRANCH" =~ ^rad/[a-z0-9][a-z0-9-]*$ ]]; then
echo "✗ Invalid or missing Branch field: '${WORK_BRANCH:-<missing>}' (expected rad/<feature>)."
echo " This plan predates the branch-at-creation workflow. Recreate it with /rad-plan, or add the Branch field manually."
exit 1
fi
Step 2: Verify the plan is approved
The gate evaluates the appended approved event over the feature's event log
(.agents/state/<feature>/events.jsonl) — the event log is the approval
authority. The plan-doc Status: header is display-only and is not consulted by
the gate. The check still runs against the plan's own branch tip:
scripts/check-plan-approved.sh "$WORK_BRANCH"
If not approved:
✗ Cannot execute: plan is not yet approved.
Plan: [plan file]
Branch: [work branch]
The architect must run /rad-approve [feature-name] before execution can begin.
Stop. Do not proceed.
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 · 374 lines · 80 tokens per session scan A 015e8c143531
rad-deliver is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 3,167 once invoked, about $0.0004 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.