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/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.
<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="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.00807 |
| Opus 5.5 | $0.00040 | $0.00323 |
| Sonnet 5.5 | $0.00020 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00081 |
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 21d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rad-deliver
Deliver an approved plan. All the work happens inside one command,
node harness/cli.js deliver: the approval gate, wave execution, the test
gates, the finish commits, labels and the deliver PR. Your job is to run it,
report what it says, and hand any decision back to the user.
Input
The input — $ARGUMENTS — names the plan by its first token:
feature-name→ the feature slug.agents/plans/feature-name.md→ the slug isfeature-name
If the input is empty, list the features and their status with
node harness/cli.js status, show the user the ones marked approved, and
ask which to deliver. Do not pick one yourself.
Step 1: Run the delivery
node harness/cli.js deliver <feature>
A delivery runs every wave of the plan and can take a long time. Run it in the background where your tool supports that and wait for it to finish; do not poll it in a tight loop. Keep its full output — the result lines are at the end.
Step 2: Act on the exit code
-
0 — delivered. Report the summary line and the PR link from the output.
-
1 — failed. Report the
rad deliver: failed …line from stderr — itsclass,decisionanddetailfields — and stop. Do not retry automatically and do not try to repair the work yourself; the user decides what happens next. -
2 — usage or configuration problem. Explain the message and how to fix it. For example, no
agent:configured → setagent:in.rad/config.yml, or on a fresh install runnode harness/cli.js config init --agent claude(or--agent codex). Then the user re-runs this skill. -
3 — needs a decision. Show the user the
decisiontext from therad deliver: failed …line, and the exact command that resumes the run:node harness/cli.js deliver <feature> --resume --context "<your answer>"STOP and ask the user for their answer. Do not answer it yourself and do not resume on your own judgment. Only after the user answers, run that command with their answer as the
--contexttext, then act on its exit code the same way.
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.
- 21d ago Changed · -306 lines · +19 tokens per session b5daedee26e5
- 2mo 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 4d ago), licensed MIT. It adds 99 tokens to every session and 807 once invoked, about $0.0004 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.
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.