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 bestdeejay-design/agent-skills --skill chronosgit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/bestdeejay-design/agent-skills/chronos)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/chronos"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/chronos/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/bestdeejay-design/agent-skills/chronos"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/chronos.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 | $0.00118 | $0.01656 |
| Opus 5.5 | $0.00047 | $0.00662 |
| Sonnet 5.5 | $0.00024 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
chronos 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 1mo 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chronos — Documentation Timekeeper
5 AI agents for documentation integrity. Each agent is a focused skill invoked by the Chronos orchestrator.
What it does
Chronos audits project documentation for:
- Duplicates — documents with high similarity (Censor)
- Broken links — references to non-existent files (Censor)
- Missing required docs — mandatory files per classification level (Dewey)
- Orphans — documents with no inbound references (Dewey)
- Classification — document type: L1 Contracts → L6 Auxiliary (Dewey + Canon)
- Stale data — dates older than threshold (Veles)
Agents
| Agent | Role | Trigger |
|---|---|---|
| Chronos | Orchestrator — runs the full Pantheon | chronos --preset full |
| Censor | Fact-checker — duplicates + broken links | chronos --preset minimal |
| Dewey | Classifier — L1-L6 taxonomy + missing/orphans | chronos --preset standard |
| Veles | Statistician — staleness, metrics, trends | chronos --preset full |
| Canon | Truth-keeper — cross-ref validation against contracts | chronos --preset standard |
Usage
# Basic audit (duplicates + links only)
chronos --path .
# Standard: check + classify (Censor + Dewey + Canon)
chronos --path . --preset standard
# Full Pantheon: all 5 agents
chronos --path . --preset full
# JSON output for CI
chronos --path . --output json --output-file report.json
# Fail on critical findings
chronos --path . --fail-on critical
# Single agent
chronos --path . --agent censor
Presets
| Preset | Agents | Use case |
|---|---|---|
minimal |
Censor | Quick CI gate — duplicates + broken links |
standard |
Censor + Dewey + Canon | PR validation — check + classify + cross-ref |
full |
All 5 agents | Release audit — complete integrity + staleness |
Document Hierarchy (L1–L6)
L1: Contracts — Machine truth (OpenAPI, AsyncAPI, JSON Schema)
L2: Product Canon — Human truth (VISION, PRD, ROADMAP, FEATURES)
L3: Engineering Canon— Implementation truth (ARCHITECTURE, ADR, SAGA)
L4: Derived — Synthesized (REFERENCE, TEST_CASES, DEV_GUIDE)
L5: Artifacts — Generated (API docs, changelogs, diagrams)
L6: Auxiliary — Supporting (README, CONTRIBUTING, templates)
What ships with it
36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .github/workflows/test.yml 667 B
- .gitignore 681 B
- CHANGELOG.md 1.1 KB
- CONTRIBUTING.md 1.7 KB
- docs/ARCHITECTURE.md 12 KB
- docs/PRD.md 8.0 KB
- docs/VISION.md 8.7 KB
- LICENSE 1.0 KB
- pyproject.toml 1.1 KB
- README.md 3.2 KB
- references/AGENTS.md 713 B
- references/CLASSIFICATION.md 758 B
- references/CONFIG.md 570 B
- skill.json 2.2 KB
- src/chronos/__init__.py 334 B runs code
- src/chronos/__main__.py 61 B runs code
- src/chronos/agents/__init__.py 270 B runs code
- src/chronos/agents/base.py 689 B runs code
- src/chronos/agents/canon.py 3.9 KB runs code
- src/chronos/agents/censor.py 3.4 KB runs code
- src/chronos/agents/chronos.py 2.5 KB runs code
- src/chronos/agents/dewey.py 4.2 KB runs code
- src/chronos/agents/veles.py 3.3 KB runs code
- src/chronos/cli.py 2.1 KB runs code
- src/chronos/core/__init__.py 134 B runs code
- src/chronos/core/reader.py 1.4 KB runs code
- src/chronos/core/reporter.py 2.5 KB runs code
- tests/__init__.py 0 B runs code
- tests/test_base.py 1.8 KB runs code
- tests/test_canon.py 2.4 KB runs code
- tests/test_censor.py 2.8 KB runs code
- tests/test_chronos.py 3.5 KB runs code
- tests/test_dewey.py 3.8 KB runs code
- tests/test_reader.py 3.2 KB runs code
- tests/test_reporter.py 2.6 KB runs code
- tests/test_veles.py 2.6 KB runs code
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.
- 1mo ago Changed · -4 lines 60291b61cf3a
- 1mo ago First seen · 212 lines · 118 tokens per session scan A f5a9d638efe8
chronos is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,656 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
nextcloud-files
Browse and manage Nextcloud files and folders over WebDAV via the nextcloud-agent MCP server — list a directory, read/download a file, upload, create/delete/move/copy, and read properties. Use when the agent must navigate a Nextcloud file tree, fetch a document's bytes, or reorganize storage. Do NOT use for sharing…
obsidian-organizer
File new notes into the right folder and audit/reorganize folder structure in the user's Obsidian vault, using the obsidian CLI and a single source-of-truth map note (00Index/FolderMap.md) that lives inside the vault. Use this whenever a note needs to be placed, filed, sorted, or moved into the vault; whenever the…
obsidian-vault-builder
Use when adding/editing/querying content in an existing Obsidian vault, configuring plugins, integrating Claude Code with Obsidian via Local REST API or CLI, automating ongoing capture/organization/retrieval, designing a personal knowledge management workflow, OR building academic study vaults (course prep…
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.
notes
A note-management guide for searching, reading, creating, and adding content to personal notes through an API.