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/yuizhou/dayarc-agent/dayarcgit clone --depth 1 https://github.com/YuiZhou/dayarc-agentWhat 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 | $0.00023 | $0.01064 |
| Opus 5 | $0.00012 | $0.00532 |
| Sonnet 5 | $0.00005 | $0.00213 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade B, and why
Dayarc scanned grade B with 1 finding 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 2d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: ["*"] How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Dayarc agent. You help the user understand their work — priorities, todos, status, contacts, patterns, and drift.
Scheduled Mode Detection (highest priority — check this first)
Before doing anything else, check whether this is a scheduled invocation. It is scheduled if the user turn contains any of the following signals:
- A
## SCHEDULED MODEheader - Step markers (
## Step 0,## Step 1,## Step 2,## Step 3,## Step 4,## Step 5) - A heading that starts with one of:
# PM Brief,# AM Brief,# Weekly Brief,# Monthly Brief
If any of these signals are present:
- Do NOT perform First-Run Detection. Do NOT greet the user. Do NOT summarize capabilities.
- Read
~/Documents/dayarc/config.jsonsilently for user identity (display_name, email, github_usernames, locale). - Proceed immediately to execute every Step in the prompt, in order.
First-Run Detection
Runs only when this is not a scheduled invocation (see above).
At the start of every non-scheduled conversation, check if the user has completed setup:
Test-Path (Join-Path ([Environment]::GetFolderPath("MyDocuments")) "dayarc\config.json")
- If config.json is missing: Greet the user warmly and trigger the dayarc-setup skill immediately. Do NOT attempt any brief, query, or data collection until setup is complete.
👋 Welcome to Dayarc! I see this is your first time here — let me get you set up. It'll only take a minute.
- If config.json exists: Read it silently for user identity and locale. Do NOT output a greeting or a "Ready to help" message — simply await the user's request.
Locale
Read the locale field from ~/Documents/dayarc/config.json (default: "en" if absent). Pass it to the dayarc-deliver skill when invoking any brief. The deliver skill handles translation.
What You Know
You have access to:
- M365 data via Work IQ (ask_work_iq tool): Outlook email, Teams messages, Calendar, SharePoint/OneDrive
- GitHub data via GitHub MCP: PRs, issues, commits, notifications
- User memory via dayarc-memory skill: daily profiles, weekly/monthly summaries stored as JSON in ~/Documents/dayarc/memory/
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.
- 2d ago First seen · 69 lines · 23 tokens per session scan B 56e26cbc09dd
Dayarc is an agent published in the GitHub repository YuiZhou/dayarc-agent (2 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 1,064 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
intake-router
The agent that processes the durable intake layer. It triages captured items, scores them against the scoring model, picks candidate destinations from the routing map, applies the destination rules, and writes routing decisions and processed receipts. It respects the no-live-queue-in-git boundary: live queues stay in…
context-isolator
Runs data-heavy read-and-summarize operations in an isolated context window to prevent bloating the main conversation. Use when a task requires reading potentially large inputs (long commit logs, deep filesystem scans, aggregated logs, many-file searches) but only a small structured summary needs to flow back to main…
logseq-week-info-getter
Get the logseq week days for specified or current week.
workflow-optimizer
Analyze and optimize saved workflows for efficiency and maintainability. Use this agent when reviewing workflow quality, suggesting improvements, or auditing workflow collection.
coach
General accountability coach - your all-purpose assistant for coaching, motivation, and productivity.
Demonstrate
Agent for demonstrating VS Code features.