present-pr

present-pr is a command for coding agents from bruno-rv/premium-presentations. It costs 17 tokens per session (1,679 once invoked), scanned A, original, MIT.

A command that turns a pull request—the proposed code change for review—or a range of commits into a presentation deck based on the actual code differences.

In plain words
What is it for?
Use it to create a validated presentation for reviewing or presenting a pull request, following an existing deck-generation process.
Why use it?
It reduces the work of explaining a code change while checking that the slides match the real diff and contain no invented or unfinished content.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the premium-presentations plugin — 1 skill, 3 commands shipped together

Install

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.

agentmods
npx agentmods add commands/bruno-rv/premium-presentations/present-pr
Clone the repo
git clone --depth 1 https://github.com/bruno-rv/premium-presentations

Or install premium-presentations, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 present-pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/bruno-rv/premium-presentations/present-pr.svg)](https://agentmods.dev/commands/bruno-rv/premium-presentations/present-pr)
Your own site
<a href="https://agentmods.dev/commands/bruno-rv/premium-presentations/present-pr"><img src="https://agentmods.dev/badge/commands/bruno-rv/premium-presentations/present-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.01679
Opus 5 $0.00009 $0.00839
Sonnet 5 $0.00003 $0.00336
Haiku 4.5 $0.00002 $0.00168

Measured 5d ago against content hash a0eea8bb7a5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

present-pr 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 5d 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.

commands/present-pr.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn the current branch's PR (or commit range) into a deck_doctor-green premium deck grounded in the real diff — no invented content, no placeholder slides. This funnels into the existing premium-presentations skill pipeline verbatim: new-deck.sh → spec → generate → deck_doctor.py. Do not emit slides directly and do not bypass the spec contract.

0. Set provider paths

Claude Code keeps the installed plugin immutable. Capture its bundled skill from CLAUDE_PLUGIN_ROOT, and write every generated artifact beneath the active project in CLAUDE_PROJECT_DIR:

plugin_root="${CLAUDE_PLUGIN_ROOT}"
if [ -z "$plugin_root" ]; then
  echo "present-pr: CLAUDE_PLUGIN_ROOT is required" >&2
  exit 1
fi
skill_root="$plugin_root/skills/premium-presentations"
project_root="${CLAUDE_PROJECT_DIR}"
if [ -z "$project_root" ]; then
  echo "present-pr: CLAUDE_PROJECT_DIR is required" >&2
  exit 1
fi
deck_root="$project_root/assets/decks"
themes_css="$project_root/assets/shared/premium-themes.css"
if [ ! -f "$themes_css" ]; then
  themes_css="$skill_root/assets/shared/premium-themes.css"
fi
cd "$project_root"

The cd is deliberately after both roots are captured. All subsequent commands use these absolute paths; do not substitute cwd-relative skills/premium-presentations paths.

1. Determine the base ref

Resolve one base commit and reuse it for every diff/log below — never inline a literal main in the git commands themselves, since main may not exist locally (worktrees, orphan branches, shallow clones).

resolve_base() {
  # 1. Explicit argument always wins.
  if [ -n "$1" ]; then
    echo "$1"
    return 0
  fi
  # 2. Real PR ancestry: where this branch forked from main.
  local fork_point
  fork_point="$(git merge-base --fork-point main HEAD 2>/dev/null)"
  if [ -n "$fork_point" ]; then
    echo "$fork_point"
    return 0
  fi
  # 3. main exists locally and actually diverges from HEAD (not just a
  #    missing fork-point cache entry, e.g. a shallow clone).
  if git show-ref --verify --quiet refs/heads/main; then
    local mb head
    mb="$(git merge-base main HEAD 2>/dev/null)"
    head="$(git rev-parse HEAD)"
    if [ -n "$mb" ] && [ "$mb" != "$head" ]; then
      echo "$mb"
      return 0
    fi
  fi
  # 4. No usable main (orphan branch, worktree without main, or HEAD==main):
  #    the same synthetic stand-in the skill's own test fixtures use.
  if git rev-parse --verify --quiet HEAD~3 >/dev/null 2>&1; then
    echo "HEAD~3"
    return 0
  fi
  # 5. History too short even for HEAD~3 (shallow clone, brand-new repo):
  #    fall back to the root commit, or fail loudly rather than guess.
  local root
  root="$(git rev-list --max-parents=0 HEAD 2>/dev/null | tail -1)"
  if [ -n "$root" ] && [ "$root" != "$(git rev-parse HEAD)" ]; then
    echo "$root"
    return 0
  fi
  echo "present-pr: cannot resolve a comparison base — no main branch, no fork-point, and fewer than 3 commits of history. Pass an explicit base ref: /present-pr <base>" >&2
  return 1
}

base="$(resolve_base "$1")" || exit 1

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 17 tokens per session scan A a0eea8bb7a5c

Subscribe to this mod's changes

present-pr is a command published in the GitHub repository bruno-rv/premium-presentations (3 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,679 once invoked, about $0.0001 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.