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 skills add SebastianElvis/reaper --skill synthesizegit clone --depth 1 https://github.com/SebastianElvis/reaperWrote 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/skills/sebastianelvis/reaper/synthesize)<a href="https://agentmods.dev/skills/sebastianelvis/reaper/synthesize"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/synthesize/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/skills/sebastianelvis/reaper/synthesize"><img src="https://agentmods.dev/badge/skills/sebastianelvis/reaper/synthesize.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 | $0.00048 | $0.02156 |
| Opus 5 | $0.00024 | $0.01078 |
| Sonnet 5 | $0.00010 | $0.00431 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
synthesize 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 12d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize
Generate a formal research paper from all investigation results. The output should read like a publishable academic paper — not a consulting report or investigation diary.
Usage
Invoke this skill by name; no arguments required. On slash-command hosts, prefix with / (e.g. /synthesize).
synthesize
Instructions
1. Re-read Workspace State (Efficiently)
Do NOT rely on context window. Re-read workspace files, but load selectively to stay within context limits:
Always read:
reaper-workspace/notes/current-understanding.md— the accumulated findings (primary source)reaper-workspace/notes/results.md— the cycle-by-cycle record including batch summariesreaper-workspace/notes/problem-statement.md— model assumptions and property definitionsreaper-workspace/notes/ideas.md— the ideas and their resolution status
Read for background (skim, don't deep-read):
reaper-workspace/notes/paper-summary.md— focus on "Problem Statement" and "Red Flags" sections (skip if not present)reaper-workspace/notes/literature.md— focus on "Landscape Summary" and "Key Prior Results" sections
Load investigation directories selectively:
- Read
notes/results.mdbatch summaries first — these provide a condensed view of each batch's findings - Only read
investigations/*/analysis.mdfor keep hypotheses (check the "Status" column innotes/results.md). Skip discard investigations entirely. Eachanalysis.mdreflects the latest state of its hypothesis (edited inline on revisit). - If batch summaries are present and sufficient, you may skip individual
analysis.mdfiles for cycles already summarized - For investigations with formal proofs (
proof.md), only read if the report needs to cite a specific proof step
2. Identify the Central Result
If the investigation yielded multiple results, identify the single most important one. This is the main theorem of the paper. Ask: "If the reader remembers only one thing, what should it be?"
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.
- 12d ago First seen · 189 lines · 48 tokens per session scan A a4a961bf866f
synthesize is a skill published in the GitHub repository SebastianElvis/reaper (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,156 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 2026-08-31.
Other skills, from other repositories
literature-review-agent
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to…
agent-research-aggregator
Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…
content-refinement-agent
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…
paper-orchestra
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…
section-writing-agent
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…
plotting-agent
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…