prisma

prisma is a command for Claude Code from Abhinavbwj/AEC-Scholar. It costs 23 tokens per session (535 once invoked), scanned A, original, MIT.

A generator for PRISMA 2020 reporting materials, including a Mermaid flow diagram and checklist for systematic or scoping reviews. PRISMA is a reporting standard that shows how studies were found, screened, and included.

In plain words
What is it for?
Use it to document database searches, duplicate removal, screening, retrieval problems, eligibility exclusions, other search methods, and included studies.
Why use it?
It helps turn review-search counts and exclusion reasons into a traceable account of the selection process. If counts are missing, it provides a structure for collecting them.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

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.

agentmods
npx agentmods add commands/abhinavbwj/aec-scholar/prisma
Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/AEC-Scholar

Made for: Claude Code.

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

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 prisma

README.md
[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/prisma.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/prisma)
Your own site
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/prisma"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/prisma.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00535
Opus 5 $0.00012 $0.00267
Sonnet 5 $0.00005 $0.00107
Haiku 4.5 $0.00002 $0.00053

Measured 6d ago against content hash a2fbca58a4a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prisma 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 6d 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.

aec-scholar/commands/prisma.md · 42 lines

What it actually says

Generate PRISMA 2020 reporting artifacts for the user's review. Use the systematic-review skill.

Context / counts provided: $ARGUMENTS

  1. Collect the counts. If the user gave numbers, use them. Otherwise ask for (or template) the required figures: records identified per database (list each), duplicates removed, records screened and excluded, reports sought/retrieved/not-retrieved, reports assessed and excluded with reasons + counts, records from other methods (snowballing/websites), and final studies included.

  2. Render the flow diagram as Mermaid (so it displays in the terminal/markdown). Use the PRISMA 2020 structure: Identification → Screening → Included, with a parallel "other methods" branch if applicable. Example skeleton to fill:

    flowchart TD
      A[Records identified:\nScopus n=__, WoS n=__] --> B[Duplicates removed n=__]
      B --> C[Records screened n=__]
      C -->|Excluded n=__| X1[ ]
      C --> D[Reports sought for retrieval n=__]
      D -->|Not retrieved n=__| X2[ ]
      D --> E[Reports assessed for eligibility n=__]
      E -->|Excluded n=__:\nreason1 n=__, reason2 n=__| X3[ ]
      E --> F[Studies included n=__]
      G[Other methods:\nsnowballing n=__] --> E
    

    Also offer the official PRISMA2020 R package / flow-diagram generator as an alternative for the publication-ready figure.

  3. Produce the PRISMA 2020 checklist (27 items) as a table mapping each item to where it is reported in the manuscript (section/page), so the user can submit it as supplementary material. Use PRISMA-ScR if the review is a scoping review.

  4. Sanity-check the numbers add up (identified − duplicates = screened; screened − excluded = assessed; etc.) and flag any inconsistency.

Integrity: never invent counts. If numbers are missing, leave clearly marked placeholders for the user to fill, and do not present a fabricated flow as complete.

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. 6d ago First seen · 42 lines · 23 tokens per session scan A a2fbca58a4a0

Subscribe to this mod's changes

prisma is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 535 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.