distill-pr-intent

distill-pr-intent is a skill for Claude Code from openclaw/clawdinators. It costs 27 tokens per session (507 once invoked), scanned A, original, MIT.

A procedure for summarising the purpose of one OpenClaw pull request. A pull request is a proposed code change for review and merging.

In plain words
What is it for?
Reviewing one OpenClaw pull request, examining its code diff, and writing a concise memo about the author’s goal and the problem addressed.
Why use it?
It produces a short, evidence-based explanation of the change without making guesses or modifying the repository or pull request.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Good fit Reviewing one OpenClaw pull request, examining its code diff, and writing a concise memo about the author’s goal and the problem addressed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openclaw/clawdinators/distill-pr-intent
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.

Any agent
npx skills add openclaw/clawdinators --skill distill-pr-intent
Clone the repo
git clone --depth 1 https://github.com/openclaw/clawdinators

Made for: Claude Code.

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 distill-pr-intent

README.md
[![agentmods](https://agentmods.dev/badge/skills/openclaw/clawdinators/distill-pr-intent.svg)](https://agentmods.dev/skills/openclaw/clawdinators/distill-pr-intent)
Your own site
<a href="https://agentmods.dev/skills/openclaw/clawdinators/distill-pr-intent"><img src="https://agentmods.dev/badge/skills/openclaw/clawdinators/distill-pr-intent.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00027 $0.00507
Opus 5 $0.00014 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 8d ago against content hash 3cb519ad69ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

distill-pr-intent 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 8d 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.

clawdinator/workspace/skills/distill-pr-intent/SKILL.md · 70 lines

What it actually says

Distill PR Intent (single PR, stdout-only)

Goal

Given one PR number in openclaw/openclaw, output a short memo answering:

What was the author trying to accomplish (motivation / problem framing / bet), as evidenced by the code change?

Inputs

  • Required: PR number (assume repo openclaw/openclaw).

Rules

  • No external side effects: no comments, labels, merges, pushes.
  • Prefer code-derived intent. PR title/body are secondary.
  • Do not guess. If intent is unclear from artifacts, say so.
  • Keep output short + stable. No telemetry/timing in the memo.

Output format (stdout)

PR INTENT (openclaw#<PR>)

<free prose, up to ~5 sentences; keep under ~10 lines>

Mechanical steps (deterministic)

  1. Work in the OpenClaw repo worktree tooling:
cd /var/lib/clawd/repos/openclaw
scripts/pr review-init <PR>
scripts/pr review-checkout-pr <PR>

source .local/review-context.env
  1. Gather diff artifacts:
git diff --name-status "$MERGE_BASE"..HEAD > .local/intent.name-status.txt
git diff --stat "$MERGE_BASE"..HEAD > .local/intent.stat.txt

# Patch budget: 200KB
patch_bytes=$(git diff "$MERGE_BASE"..HEAD | wc -c | tr -d ' ')
if [ "$patch_bytes" -le 200000 ]; then
  git diff "$MERGE_BASE"..HEAD > .local/intent.patch.txt
  echo PATCH_OK > .local/intent.patch-mode.txt
else
  : > .local/intent.patch.txt
  echo TOO_LONG > .local/intent.patch-mode.txt
fi
  1. Distill intent:
  • If PATCH_OK: infer intent from .local/intent.patch.txt.
  • If TOO_LONG: infer intent from .local/intent.name-status.txt + .local/intent.stat.txt.

If multiple intents exist, mention 2–3 briefly.

If nothing coherent: say Intent unclear: ....

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. 8d ago First seen · 70 lines · 27 tokens per session scan A 3cb519ad69ed

Subscribe to this mod's changes

distill-pr-intent is a skill published in the GitHub repository openclaw/clawdinators (158 stars, last pushed 28d ago), licensed MIT. It adds 27 tokens to every session and 507 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 2026-08-30.