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 KaelinGraf/redraft --skill redraft-reportgit clone --depth 1 https://github.com/KaelinGraf/redraftWrote 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/kaelingraf/redraft/redraft-report)<a href="https://agentmods.dev/skills/kaelingraf/redraft/redraft-report"><img src="https://agentmods.dev/badge/skills/kaelingraf/redraft/redraft-report/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/kaelingraf/redraft/redraft-report"><img src="https://agentmods.dev/badge/skills/kaelingraf/redraft/redraft-report.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 | $0.00052 | $0.00548 |
| Opus 5 | $0.00026 | $0.00274 |
| Sonnet 5 | $0.00010 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
redraft-report 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are rendering the project's design graph into a technical document — the redraft organizing protocol's §7 report flow. The server assembles the structure; you write the prose. The graph is the only source of truth.
Steps
-
Assemble. Call
assemble_report(root_id)for the spine root the report should cover (list roots via theoverviewtool orgraph://project/rootif unsure; a topical brief usesbriefing(query)instead). The bundle carries the section tree,decision_tablesgrouped by driver, open questions, and contradictions. -
Write LaTeX. Author the report as a LaTeX document (
\section/\subsectionmirroring the spine,tabularfor decision tables, itemize for requirement lists). Structure for a full report: executive summary → architecture → design specification → decision record (every table: accepted rows first, rejected rows WITH their tradeoffs) → requirements & constraints → timeline → open questions & gaps → graph statistics. -
Ground every claim. Every factual statement must trace to a node body, title, status, or edge in the bundle. Where the graph carries no rationale, write
—and name the gap in prose — a gap is a finding, not an embarrassment. NEVER present arejecteddecision as adopted; statuses are load-bearing. -
Save + snapshot. Write to
reports/<YYYY-MM-DD>-<short-slug>.texin the graph repo, then callsnapshot("<what the report covers>"). The operator UI's Reports tab lists and renders it immediately.
What NOT to do
- Never invent rationale, tradeoffs, or context the graph does not carry — silence in the graph is silence in the report (or an entry under gaps).
- Never grep or read
graph/nodes/*.mdto gather material — the bundle and retrieval tools are the read path (protocol: "Reading the graph"). - Don't paste raw node bodies wholesale; synthesize prose a zero-context engineering reviewer can read, with the graph's claims intact.
- Lightweight recurring summaries (
/summary) stay markdown per the protocol; this skill is for formal technical reports.
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 · 43 lines · 52 tokens per session scan A acd3f88802b8
redraft-report is a skill published in the GitHub repository KaelinGraf/redraft (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 548 once invoked, about $0.0003 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
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
neo4j-knowledge-graph
Use when designing, importing, querying, or modernizing Neo4j knowledge graphs from CSV, Excel, pandas, Cypher, py2neo, the official neo4j Python driver, vector indexes, or GraphRAG workflows.
decision-records
Use when a hard-to-reverse choice (database, framework, vendor, auth model) must be frozen as an immutable numbered ADR — the context that forced it, the options weighed, the decision, consequences both ways — or superseded without erasing history. NOT a meeting recap (that is meeting-notes), NOT standing project…
data-science-analysis
Computes a numeric or categorical answer to a quantitative data-science question by cleaning and analyzing local data files (CSV, Excel, TSV, and scientific formats .npz/.fits/.h5) with pandas, numpy, and scipy. Use whenever a task ships its own dataset (in whatever local directory it provides) and asks you to derive…