prism-review-pr

prism-review-pr is a skill for Claude Code, Codex from Shailesh200/prism. It costs 71 tokens per session (674 once invoked), scanned A, original, MIT.

A pull-request and code-change review method that checks a diff together with the other code that depends on it.

In plain words
What is it for?
Use it to review pull requests or working-tree changes, assess risk, and investigate the affected files and symbols before merging.
Why use it?
Reading only changed lines can miss wider effects, such as a small edit to a widely used module.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review pull requests or working-tree changes, assess risk, and investigate the affected files and symbols before merging.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shailesh200/prism/prism-review-pr
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 Shailesh200/prism --skill prism-review-pr
Clone the repo
git clone --depth 1 https://github.com/Shailesh200/prism

Made for: Claude Code, 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 prism-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/shailesh200/prism/prism-review-pr/github.svg)](https://agentmods.dev/skills/shailesh200/prism/prism-review-pr)
Your own site
<a href="https://agentmods.dev/skills/shailesh200/prism/prism-review-pr"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-review-pr/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 prism-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/shailesh200/prism/prism-review-pr"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 674 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 $0.00071 $0.00674
Opus 5 $0.00036 $0.00337
Sonnet 5 $0.00014 $0.00135
Haiku 4.5 $0.00007 $0.00067

Measured 4d ago against content hash 35055d393877, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prism-review-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 4d 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.

packages/plugin/skills/prism-review-pr/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a change with its blast radius

Reading a diff tells you what the author wrote. It does not tell you what else depends on the lines they touched, and that is where review actually catches things. Prism can answer the second question against a local index; run it before forming an opinion.

The procedure

1. Get the change. If the user named a PR, fetch it with your GitHub tools. Otherwise call review_changes with no paths — it discovers the working-tree and branch diff itself. Do not ask the user for a list of files.

2. Understand the repository, if you do not already. repository_dna once per session, for an unfamiliar repo. Skip it for a repo you have already looked at this session; it is context, not a per-review step.

3. Read what review_changes flagged. It returns findings with paths and severities. This is the input to the next step, not the conclusion.

4. Take the blast radius of the risky paths. Call blast_radius on the flagged files and on any exported symbol the diff changed. This is the step that distinguishes this review from reading the diff: a two-line change to a widely imported module is a bigger event than a hundred lines in a leaf.

Use rename_impact when a symbol was renamed, and safe_delete when something was removed. Both answer "did the author catch every call site" much faster and more reliably than grep.

5. Name the tests that matter. test_impact on the changed paths. Report which suites cover the change, and say plainly when a risky path has no test covering it — that is one of the most useful things a review can surface.

6. Write the review. Lead with the risk, not with a file-by-file walk. Every claim about impact should cite what produced it, so the author can check it. If blast radius found nothing alarming, say so — "this is contained to the module it touches" is a real review outcome and worth stating.

7. Post it, if the user asked you to. Use your own GitHub tools to leave the review or the comments. Use your own issue-tracker tools (Linear, Jira) to move the ticket if the user asked for that too.

Read the full file on GitHub · 57 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. 4d ago First seen · 57 lines · 71 tokens per session scan A 35055d393877

Subscribe to this mod's changes

prism-review-pr is a skill published in the GitHub repository Shailesh200/prism (3 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 674 once invoked, about $0.0004 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 2026-09-05.