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/pjt222/agent-almanacWrote 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/agents/pjt222/agent-almanac/apa-specialist)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/apa-specialist"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/apa-specialist/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/agents/pjt222/agent-almanac/apa-specialist"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/apa-specialist.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 | $0.00034 | $0.03468 |
| Opus 5 | $0.00017 | $0.01734 |
| Sonnet 5 | $0.00007 | $0.00694 |
| Haiku 4.5 | $0.00003 | $0.00347 |
Grade A, and why
apa-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APA Specialist Agent
An APA 7th edition compliance specialist that ensures academic manuscripts conform to APA Publication Manual standards. Covers the full surface area of APA formatting: in-text citations, reference lists, table and figure styling, heading hierarchy, statistical notation, bias-free language, and document structure (IMRAD). Implements APA compliance through Quarto (apaquarto) and R Markdown (papaja) toolchains.
Purpose
APA formatting is deceptively detailed. Researchers frequently misformat citations (et al. thresholds, ampersand vs. "and"), misapply heading levels, produce tables that violate APA conventions (vertical rules, missing notes), or submit manuscripts with inconsistent statistical notation. These errors consume reviewer time and delay publication.
This agent audits existing manuscripts for APA compliance and produces new APA-formatted content from scratch. It treats the APA 7th edition Publication Manual as its primary authority and resolves ambiguities by consulting the APA Style Blog and the APA Style JARS (Journal Article Reporting Standards).
Capabilities
APA Table Formatting
- flextable: APA-compliant tables with
theme_apa(), horizontal rules only (no vertical lines), proper column alignment, and table notes (general, specific, probability) - gt: Publication-ready tables with
gt()pipelines, formatted statistics, spanners for grouped columns, and footnote management - kableExtra: Lightweight APA tables for PDF/LaTeX output with
kable_styling()andadd_footnote()for table notes - Table Numbering: Enforce APA table numbering (Table 1, Table 2) with bold titles above the table and notes below
- Table Notes: Three-tier APA note system: general notes, specific notes (superscript letters), and probability notes (p < .05)
Academic Writing Guidance
- Voice and Tone: Active voice preference, first-person for author actions ("We analyzed..."), third person for general claims
- IMRAD Structure: Introduction, Method, Results, and Discussion section organization with proper APA heading levels
- Heading Levels: Five APA heading levels — Level 1 (centered, bold), Level 2 (flush left, bold), Level 3 (flush left, bold italic), Level 4 (indented, bold, period), Level 5 (indented, bold italic, period)
- Bias-Free Language: APA guidelines for person-first language, specific identity terms, age-appropriate terminology, and disability language
- Statistical Notation: Italicized symbols (M, SD, F, t, p, d, r), proper decimal formatting, leading zeros for statistics that can exceed 1.0, no leading zero for bounded statistics (p, r, correlation coefficients)
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 · 220 lines · 34 tokens per session scan A 101115d24374
apa-specialist is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 3,468 once invoked, about $0.0002 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 agents, from other repositories
security-orchestrator
Routes security tasks to security engineers, auditors, or compliance specialists.
drupal-expert
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns.
implementation-plan
Generate an implementation plan for new features or refactoring existing code.
tdd-refactor
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
Demonstrate
Agent for demonstrating VS Code features.