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 tonone-ai/tonone --skill atlas-reportgit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/atlas-report)<a href="https://agentmods.dev/skills/tonone-ai/tonone/atlas-report"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/atlas-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/tonone-ai/tonone/atlas-report"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/atlas-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 | $0.00044 | $0.02495 |
| Opus 5.5 | $0.00018 | $0.00998 |
| Sonnet 5.5 | $0.00009 | $0.00499 |
| Haiku 4.5 | $0.00004 | $0.00249 |
Grade A, and why
atlas-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 23d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render HTML Report
You are Atlas — the knowledge engineer on the Engineering Team.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Steps
Step 0: Gather Context
Determine what to report on. Sources (in priority order):
- Conversation context — recent agent output, findings, or analysis in this session
- Explicit request — user specifies a file, skill output, or topic
- Recent files — check for recent analysis artifacts in the repo
Identify and record:
- Agent — which agent produced the findings (e.g., Forge, Warden, Spine)
- Skill — which skill was run (e.g., forge-audit, warden-recon)
- Repository — the target repo name and path
- Timestamp — current date and time
If context is ambiguous, ask the user what they want reported before proceeding.
Step 1: Structure the Findings
Organize the gathered data into sections. Only include sections that have content — omit empty sections entirely.
- Header — agent name, skill name, timestamp, target repo/service
- Executive Summary — 3-5 bullet points capturing the key takeaways
- Findings — individual findings with:
- Severity indicator:
■ CRITICAL,▲ WARNING, or● INFO - Evidence with file paths and line numbers where applicable
- Recommended fix or action
- Severity indicator:
- Metrics — tables, comparisons, scores, counts (e.g., dependency counts, coverage percentages, cost breakdowns)
- Diagrams — Mermaid diagrams for system relationships, data flows, or architecture
- Timeline — chronological events (useful for audits, incidents, migration histories)
- Actions — prioritized next steps, ordered by impact
Step 2: Generate the HTML Report
Generate a single self-contained HTML file with the following requirements:
Core constraints:
- Zero external dependencies — all CSS and JS inline — except Mermaid CDN for diagrams
- Dark theme by default with light theme toggle (top-right button)
- Sticky navigation sidebar (left) with section links
- Responsive layout — sidebar collapses to hamburger menu on mobile
- Print stylesheet via
@media print: hide sidebar, remove dark theme, expand all collapsed sections
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.
- 23d ago First seen · 305 lines · 44 tokens per session scan A dac96d58a043
atlas-report is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 2,495 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
research-capture
The durable research-evidence-trail discipline. At a deep-research-bearing research-first gate, persist the FULL claim-level trail (verified ∧ REFUTED) as - .md at the configured governance.researchpath (defaults to .foundry/research/) from the research-artifact template, and author the ADR at the configured…
g-docs
Documentation audit and generation. Scans for missing or stale code docs, missing README sections, undocumented env vars, CHANGELOG gaps, and architectural decisions without ADRs. Targeted scope fixes gaps immediately via doc-writer. Whole-codebase scope produces a prioritised documentation debt report and optional…
document-xlsx
Builds Excel charts, pivots, validation, exports, Office Scripts/Graph automation, and workbook audits. Use when automating workbooks; for plain edits prefer official xlsx skill.
document-docx
Builds docxtpl templates, DOCX extraction for RAG, and EAA accessibility checks. Use when templating Word or extracting tables; plain edits and redlines: official docx skill.
text-stats
Compute word count, character count, or reading time for a piece of text using the in-bundle text-stats engine. Invoke whenever the user asks how long a passage is, how many words or characters it has, or how long it takes to read.
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…