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 techwolf-ai/ai-first-toolkit --skill triage-messagesgit clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkitWrote 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/techwolf-ai/ai-first-toolkit/triage-messages)<a href="https://agentmods.dev/skills/techwolf-ai/ai-first-toolkit/triage-messages"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/triage-messages/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/techwolf-ai/ai-first-toolkit/triage-messages"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/triage-messages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00996 |
| Opus 5.5 | $0.00025 | $0.00398 |
| Sonnet 5.5 | $0.00012 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
triage-messages 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Messages
Principle: "You are responsible." This skill surfaces and categorises. The manager decides what to act on and how.
Scans unread Slack messages and recent emails, categorises them by urgency and type, and presents a prioritised overview.
When to Use
- Morning routine: catch up on what happened overnight
- After a block of focus time or meetings
- When the manager says "what did I miss?", "catch me up", "triage my messages"
- Can be scoped to a time window: "triage since yesterday", "triage last 2 hours"
Instructions
If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.
1. Determine Time Window
Default: since the manager's last likely check-in (use calendar to estimate, if they were in back-to-back meetings for 3 hours, scan those 3 hours).
If specified: use the provided time window.
If unclear, ask:
What time period should I triage? Options:
- Since this morning
- Last [N] hours
- Since yesterday
- Custom range
2. Load Manager Context
Read from manager-context/ (if available):
manager-profile.md: to know who the direct reports are (their messages get higher priority)terminology.md: to decode internal shorthand in messagesteam/: to understand team members' projects and responsibilitiessources.md: to know which customer/project channels to monitor
3. Scan Slack
Search for messages in the time window:
Priority channels (scan first):
- Channels where the manager was @-mentioned
- DMs to the manager
- Team channels (from manager-context)
- Customer/project channels (from manager-context)
Broader channels (scan for relevance):
- Company-wide channels
- Cross-functional channels the manager is in
For each message/thread, capture:
- Who sent it
- Channel
- Content summary (1 line)
- Whether the manager was mentioned or it's in a direct thread
- Link to the message
4. Scan Email
Search Gmail for messages in the time window:
What ships with it
2 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.
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 First seen · 133 lines · 62 tokens per session scan A dc0fa85da2c0
triage-messages is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (138 stars, last pushed 29d ago), licensed MIT. It adds 62 tokens to every session and 996 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 2026-08-30.
Other skills, from other repositories
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
managing-personal-crm
Use when the user asks to capture a relationship interaction, prepare for one person, clean up or reconstruct Person notes, review overdue relationships, discover who could help with current work, when another workflow finds a possible relationship effect, or when the user later confirms or revises a required catch-up…
reviewing-meetings
Use when the user asks to review, process, import, catch up on, or check for newly completed meetings from a configured meeting source, including Granola; when a scheduled post-meeting review invokes it; or when the user later revisits, resumes, approves, edits, defers, skips, or otherwise decides visible…
personal-chief-of-staff
Use when the user wants to complete a daily journal or wind down, requests a daily chief-of-staff review or a weekly or quarterly review, asks to set up, list, add, update, or remove chief-of-staff source mappings, approves, resumes, or otherwise decides visible chief-of-staff actions, or another workflow requests…
agent-cli-developer
Specialist subagent: Command-line tool development, argument parsing, interactive prompts, and terminal UI specialist. Use when building CLI tools, implementing interactive terminal interfaces, or designing command-line experiences. Trigger phrases: CLI, command-line, argument parsing, interactive prompt, shell…