pr-blocker-summarizer

pr-blocker-summarizer is a skill for Claude Code from FrancyJGLisboa/agent-skill-creator. It costs 54 tokens per session (728 once invoked), scanned A, original, MIT.

A tool that turns a JSON export of open pull requests into a short report focused first on blockers. Pull requests are proposed code changes awaiting review or merging.

In plain words
What is it for?
Summarizing PR status, identifying blocked changes, listing merge-ready requests, and producing a standup-style count.
Why use it?
It quickly separates requests with failing checks, requested changes, or staleness from those ready to merge, making review backlog easier to triage.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-skill-creator plugin — 5 skills, 1 plugin shipped together

Good fit Summarizing PR status, identifying blocked changes, listing merge-ready requests, and producing a standup-style count.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer
About the project

Agent Skills Platform turns documented work and supporting evidence into tested, installable skills for coding agents. Teams use it to review, publish, maintain, and safely reuse agent workflows, with the catalogue entries serving as skills and plugins built for that ecosystem.

FrancyJGLisboa/agent-skill-creator · 2,378 stars · on GitHub · francyjglisboa.github.io

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 FrancyJGLisboa/agent-skill-creator --skill pr-blocker-summarizer
Clone the repo
git clone --depth 1 https://github.com/FrancyJGLisboa/agent-skill-creator

Made for: Claude Code.

Or install agent-skill-creator, the plugin that ships this one along with the rest of its 5 skills, 1 plugin.

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 pr-blocker-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer/github.svg)](https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer)
Your own site
<a href="https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer"><img src="https://agentmods.dev/badge/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer/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 pr-blocker-summarizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer"><img src="https://agentmods.dev/badge/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 728 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 $0.00054 $0.00728
Opus 5 $0.00027 $0.00364
Sonnet 5 $0.00011 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 10d ago against content hash 28f62d89f723, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-blocker-summarizer 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 10d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/dependency_health.py, scripts/evolve.py, scripts/review_staleness.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

references/examples/pr-blocker-summarizer/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Blocker Summarizer

Turn a JSON export of open pull requests into a blockers-first digest: which PRs are blocked (failing checks, requested changes, or stale), which are ready to merge, and a one-line count an agent can post to standup.

A bundled example skill — small but real, used to demonstrate the creator's validation, pipeline, and eval-rollout machinery.

Activation

Activates on "summarize open PRs", "what's blocking my PRs", "PR standup", "review backlog". Do not activate on general git/GitHub questions unrelated to triaging a set of PRs.

Input

A JSON array of PRs, each with title, state (open), checks (passing/failing), review (approved/changes_requested/pending), and age_days. Missing fields are treated conservatively (counted as not-blocked only when clearly ready).

Run

python3 scripts/run_pipeline.py --input prs.json --output digest.json

Output JSON shape:

{
  "total": 7,
  "blocked": [{"title": "...", "reasons": ["failing checks"]}],
  "ready": ["..."],
  "summary": "7 open · 3 blocked · 2 ready to merge"
}

Gotchas

  • blocked + ready does not equal total. A PR is ready only when checks is explicitly passing and review is explicitly approved. A PR with no blockers but a missing checks field lands in neither list and vanishes from both counts. Never narrate the summary line as if the two numbers account for every PR — say "N blocked, M ready" and leave the remainder unclaimed.
  • state is read from the input but never filtered on. A closed or merged PR left in the export is counted in total and classified like any open one. Filter the export before running if it may contain non-open PRs.
  • review: pending counts as blocked ("awaiting review"). A PR opened five minutes ago is reported as a blocker. This is intentional for standup triage, but it inflates the blocked count on teams that open PRs early.
  • A non-numeric age_days silently skips the stale check rather than erroring. An export with "age_days": "unknown" will never flag anything stale, and the digest gives no sign that the check did not run.

Read the full file on GitHub · 73 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. 10d ago First seen · 73 lines · 54 tokens per session scan A 28f62d89f723

Subscribe to this mod's changes

pr-blocker-summarizer is a skill published in the GitHub repository FrancyJGLisboa/agent-skill-creator (2,378 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 728 once invoked, about $0.0003 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.