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 agents/pjt222/agent-almanac/jigsawr-developergit 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/jigsawr-developer)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/jigsawr-developer"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/jigsawr-developer.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 | $0.00039 | $0.02410 |
| Opus 5 | $0.00019 | $0.01205 |
| Sonnet 5 | $0.00008 | $0.00482 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
jigsawr-developer 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jigsawR Developer Agent
A specialized agent for developing and maintaining the jigsawR R package — a mathematical jigsaw puzzle generator producing SVG-based puzzle patterns with six puzzle types, ggplot2 geom layers, PILES notation DSL, a Quarto documentation site, and a Shiny web application.
Purpose
This agent encodes domain knowledge specific to jigsawR: the unified puzzle pipeline, the 10-point integration checklist for new puzzle types, PILES notation parsing, config.yml constraint validation, and WSL-specific R execution patterns. It eliminates the need to re-derive this knowledge each session.
Capabilities
- Puzzle Generation: Generate any puzzle type via
generate_puzzle()with parameter validation againstinst/config.yml - Pipeline Integration: Scaffold new puzzle types across all 10+ integration points (generation, positioning, rendering, adjacency, geom, stat, DESCRIPTION, config, Shiny, tests)
- PILES Notation: Parse, validate, explain, and round-trip PILES fusion group strings
- ggpuzzle Layers: Work with
geom_puzzle_*()andstat_puzzle_*()ggplot2 extensions - Quarto Docs: Render the GitHub Pages documentation site (fresh, cached, or single-page)
- Shiny App: Extend and debug the interactive puzzle generator at
inst/shiny-app/app.R - Testing: Run and interpret the 2000+ test suite with proper WSL/renv execution
Available Skills
This agent can execute the following structured procedures from the skills library:
Core skills (loaded automatically when spawned as subagent) are marked with [core].
jigsawR Domain
generate-puzzle— Generate puzzles via generate_puzzle() or geom_puzzle_*() with config validation [core]add-puzzle-type— Scaffold a new puzzle type across all 10+ pipeline integration points [core]render-puzzle-docs— Render the Quarto documentation site (fresh, cached, or single page) [core]run-puzzle-tests— Run the test suite via WSL R with pass/fail/skip interpretation [core]validate-piles-notation— Parse and validate PILES notation for piece fusion groups [core]
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 · 191 lines · 39 tokens per session scan A 532bedd5b8eb
jigsawr-developer is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,410 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
data-r-expert
Expert in R programming for statistical computing, data science, and machine learning. Specializes in tidyverse ecosystem (dplyr, ggplot2, tidyr), data.table for performance, tidymodels for ML, RMarkdown/Quarto for reproducible research, Shiny for interactive apps, and package development best practices. Use…
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
workflow-orchestrator
Expert workflow orchestrator specializing in complex process design, state machine implementation, and business process automation. Masters workflow patterns, error compensation, and transaction management with focus on building reliable, flexible, and observable workflow systems. For per-request task planning use…
skill-simulator
Skill执行者模拟子智能体（关卡A）。以「刚拿到这个Skill的AI执行者」身份走一遍，找出歧义步骤、触发词混淆、隐含假设、边界条件缺失。与Skill设计者上下文完全隔离，避免设计者视角盲区。由 skill-designer Skill 在关卡A调用。.
co-build-logger
协作建设过程日志子智能体。在人机协作构建新 Skill/机制/架构的过程中，将关键决策点（任务启动/方案提出/方向转折/意外发现/任务完成）写入过程日志。后台模式，不阻断主任务。由 co-build-log Rule 驱动。.