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 agentmods add commands/abhinavbwj/aec-scholar/prismagit clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWrote 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/commands/abhinavbwj/aec-scholar/prisma)<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>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 | $0.00023 | $0.00535 |
| Opus 5 | $0.00012 | $0.00267 |
| Sonnet 5 | $0.00005 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00053 |
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.
What it actually says
Generate PRISMA 2020 reporting artifacts for the user's review. Use the systematic-review skill.
Context / counts provided: $ARGUMENTS
-
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.
-
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=__] --> EAlso offer the official PRISMA2020 R package / flow-diagram generator as an alternative for the publication-ready figure.
-
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.
-
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.
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.
- 6d ago First seen · 42 lines · 23 tokens per session scan A a2fbca58a4a0
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.