assess-pr-risk

assess-pr-risk is a skill for Claude Code from tomzx/agents. It costs 0 tokens per session (4,192 once invoked), scanned A, original, MIT.

A workflow for estimating the risk of a GitHub pull request and how certain that estimate is. A pull request is a proposed code change for review before it is merged.

In plain words
What is it for?
Use it to assess a pull request using existing validation, verification, and code-review reports when they are available.
Why use it?
It separates the possible impact of a change from the strength of the available evidence. This helps a human reviewer decide whether to inspect further, proceed, or seek more checks.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to assess a pull request using existing validation, verification, and code-review reports when they are available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/assess-pr-risk
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 tomzx/agents --skill assess-pr-risk
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

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 assess-pr-risk

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/assess-pr-risk/github.svg)](https://agentmods.dev/skills/tomzx/agents/assess-pr-risk)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/assess-pr-risk"><img src="https://agentmods.dev/badge/skills/tomzx/agents/assess-pr-risk/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 assess-pr-risk

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/assess-pr-risk"><img src="https://agentmods.dev/badge/skills/tomzx/agents/assess-pr-risk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,192 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 $0.00000 $0.04192
Opus 5.5 $0.00000 $0.01677
Sonnet 5.5 $0.00000 $0.00838
Haiku 4.5 $0.00000 $0.00419

Measured today against content hash eabdc076702f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

assess-pr-risk 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 today.

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.

skills/assess-pr-risk/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assess PR Risk

Estimates how risky a pull request is and how confident that estimate is, then recommends the next action for a human reviewer. Two axes: risk is a judgment about the change (how much damage if it is wrong, how hard to undo), and confidence is a judgment about the evidence base (what could and could not be verified). The routing table turns the two scores into one next action, so the reviewer can decide at a glance. This skill judges neither code craft (that is /review-pr), conformance (/verify-pr), nor product fit (/validate-pr); it runs alongside them in parallel, never reads their reports, and never revisits their verdicts.

Prerequisites

  • Apply the shared SDLC conventions in skills/sdlc/references/shared.md (PR Review Reports for report location and posting rules).
  • If no argument is provided, target the pull request from $PR_NUMBER (and $REPO).
  • gh CLI authenticated with read access to the target repository
  • git worktree available
  • Self-contained evidence: the assessment needs only the diff, the codebase, and churn of the touched files; it never reads or waits for sibling reports (summarize-behavior-changes, adversarial-pr-review, analyze-test-coverage, validate-pr, verify-pr, review-pr)
  • Orchestrators (review-pr-full, review-requested-prs) dispatch this skill concurrently with the analyze-test-coverage -> validate -> verify -> review chain and provide WORKTREE_DIR; because it shares no evidence with the chain, the parallel dispatch never weakens the estimate.

Skill attribution (GitHub)

Before posting to GitHub, read ../github-post-attribution/SKILL.md and append the footer for SKILL_DIR = assess-pr-risk.

Communication guidelines (outbound text)

Before composing any text posted or drafted on the user's behalf, apply communication-guidelines/SKILL.md.

Workflow

Fetch PR metadata + diff ($1)
          |
          v
CLOSED or MERGED? --> note and stop
          |
          v
Create git worktree on PR branch
          |
          v
Gather evidence
(diff, codebase, tests in the diff,
 churn of touched files)
          |
          v
Score risk factors (8, each Low/Medium/High)
          |
          v
Score confidence (evidence-based rubric)
          |
          v
Route the next action (risk x confidence matrix)
          |
          v
Write assess-pr-risk.<sha>.md
Post if should-post-to-github allows
          |
          v
Clean up worktree

Read the full file on GitHub · 326 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. today Changed eabdc076702f
  2. 6d ago Changed · +11 lines 2bd1548fcff5
  3. 9d ago Changed · +8 lines b11b4626c8de
  4. 11d ago Changed · +1 lines 2bf2ebfb2c05
  5. 18d ago Changed 94f17c0c3e3d
  6. 21d ago Changed 2fa4e2f4d539
  7. 22d ago Changed · +26 lines aa832d96420b
  8. 25d ago Changed 71a2aca9a2b8
  9. 27d ago Changed · +1 lines cb98f45b2e6c
  10. 28d ago First seen · 279 lines · 0 tokens per session scan A 47785f613496

Subscribe to this mod's changes

assess-pr-risk is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,192 tokens. 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 2026-09-22.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens