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.
npx skills add Shailesh200/prism --skill prism-review-prgit clone --depth 1 https://github.com/Shailesh200/prismWrote 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.
[](https://agentmods.dev/skills/shailesh200/prism/prism-review-pr)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 4d ago First seen · 57 lines · 71 tokens per session scan A 35055d393877
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.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.