RAD_framework: Skill for Codex

.agents/skills/wrap/SKILL.md

wrap is a skill for Codex from seanrreid/RAD_framework. It costs 55 tokens per session (1,160 once invoked), scanned A, original, MIT.

A session wrap-up workflow for a RAD project. RAD is a development process that tracks work through plans, branches, commits, and review statuses.

In plain words
What is it for?
Use it to inspect session commits and uncommitted files, update plan status, add a dated progress note, and produce a session summary. It can also update and push the relevant RAD plan branch.
Why use it?
It records what happened before a work session ends, so later sessions can see the branch state, progress, and unfinished changes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: positional $N argument; installed under .agents/ (shared by several agents).

This is seanrreid/RAD_framework's own configuration. It tells 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 wrap <feature>.

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/wrap/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: 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 wrap

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/seanrreid/rad_framework/wrap"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/wrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,160 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 $0.00055 $0.01160
Opus 5.5 $0.00022 $0.00464
Sonnet 5.5 $0.00011 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 20d ago against content hash c3be42d36872, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wrap 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/wrap/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Wrap-Up

Capture what happened so the next session starts clean. No project-specific files — this works on any RAD project.

Steps

1. Gather session changes

git branch --show-current
git log --oneline @{u}.. 2>/dev/null || git log --oneline -10
git status --short

Collect the commits made this session, the current branch, and any uncommitted changes.

2. Plan status

rad deliver sets plan status — wrap records notes only and never edits Status:.

3. Append a dated progress note

If meaningful work happened on a plan but its status didn't change, append a dated line to the plan's ## Notes section (create the section if absent) so the next session has continuity:

- {date}: {one-line summary of what was done and what's next}

4. Reconcile plan vs. actual (delivery sessions only)

If on a rad/ branch with an execution log under .agents/logs/, produce a brief reconciliation note. Skip silently if there's no log.

# Find the execution log for this feature
ls .agents/logs/[feature-name]-*.md 2>/dev/null | tail -1

Check three things:

ACs covered: For each numbered AC in the plan, was it cited in a completed task commit? Note any that were deferred or skipped.

Concerns flagged: Were any tasks marked done_with_concerns? List each concern one-line so the architect sees them in the session summary without digging into the log.

Deferred items: Anything in ## Non-Goals or the wave plan that was explicitly left for a follow-up? Name it so the next session has a standing start.

Append this as a ## Session Notes block to the plan doc (create the section if absent):

## Session Notes

- {date}: Delivered Wave [N]. ACs covered: [list]. Concerns: [list or none].
  Deferred: [list or none].

4a. Publish the notes

If Step 3 or Step 4 changed the plan doc, publish it from the rad/ work branch:

Read the full file on GitHub · 144 lines

Files

What ships with it

1 file 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.

  1. 20d ago Changed · -10 lines · +3 tokens per session c3be42d36872
  2. 2mo ago First seen · 154 lines · 52 tokens per session scan A 01a120d31a32

Subscribe to this mod's changes

wrap is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,160 once invoked, about $0.0002 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.