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.
git 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/lit-review)<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/lit-review"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/lit-review/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/commands/abhinavbwj/aec-scholar/lit-review"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/lit-review.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 | $0.00021 | $0.00519 |
| Opus 5 | $0.00010 | $0.00260 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
lit-review 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 10d 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
You are running the AEC Scholar literature-review workflow. Engage the systematic-review,
aec-domains and aec-journals skills, and delegate substantial work to the literature-reviewer agent.
Target of the review: $ARGUMENTS
Proceed in this order, pausing for the user's input where a decision is theirs:
-
Clarify scope. Confirm the review type (systematic vs scoping — default to scoping if the aim is "map the field", systematic if the question is focused). Restate the objective and draft 1–3 research questions framed with PICO/PCC. State the time window and whether conference proceedings are in scope (in AEC, ISARC/CIB W78/ASCE CRC are often legitimately included — justify).
-
Protocol. Produce a concise written protocol: eligibility (inclusion/exclusion) criteria, information sources (≥2 indexed databases — recommend specific ones via
aec-journals), the synthesis method, and the quality-appraisal instrument. -
Search strategy. Build synonym-rich Boolean concept blocks (harvest AEC keyword variants from
aec-domains). Give a ready-to-run string for at least Scopus and Web of Science, noting field tags and filters. Remind the user to record per-source hit counts and the run date. -
Screening & extraction plan. Define the screening workflow (de-dup → title/abstract → full text with recorded exclusion reasons → snowballing) and a data-extraction table template.
-
PRISMA + synthesis. Set up the PRISMA 2020 flow account (counts to capture) and explain the planned thematic/framework synthesis, ending with how trends, gaps and a research agenda will be reported.
If the user supplies a set of papers, abstracts or an exported database file, screen/extract/synthesize them directly and produce the filled tables and a draft synthesis.
Integrity: never invent papers, counts, DOIs or findings. Where you reason about likely literature without verified sources, say so and tell the user exactly what to search and confirm. Use web search only to find real, verifiable sources and attribute them precisely.
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.
- 10d ago First seen · 38 lines · 21 tokens per session scan A f1863c762698
lit-review is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 519 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.