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 chiptoe-svg/nanoclaw_flexagents --skill email-archivegit clone --depth 1 https://github.com/chiptoe-svg/nanoclaw_flexagentsWrote 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/chiptoe-svg/nanoclaw_flexagents/email-archive)<a href="https://agentmods.dev/skills/chiptoe-svg/nanoclaw_flexagents/email-archive"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/email-archive/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/chiptoe-svg/nanoclaw_flexagents/email-archive"><img src="https://agentmods.dev/badge/skills/chiptoe-svg/nanoclaw_flexagents/email-archive.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 | $0.00077 | $0.02843 |
| Opus 5 | $0.00039 | $0.01422 |
| Sonnet 5 | $0.00015 | $0.00569 |
| Haiku 4.5 | $0.00008 | $0.00284 |
Grade A, and why
email-archive 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 11d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/email-archive — Email Archive
Classify and file old emails in batches. Rule-based classification handles known senders (no LLM cost). Unknown senders get LLM classification with confidence scoring.
Modes
Parse the user's command:
/email-archiveor/email-archive run→ Batch mode/email-archive status→ Status mode/email-archive review→ Review mode/email-archive recalibrate→ Recalibrate mode
If this is a scheduled task (message starts with [SCHEDULED TASK), run in batch mode.
Setup Check
test -f /workspace/group/email-archive/config.yaml && echo "CONFIG_OK" || echo "NO_CONFIG"
If NO_CONFIG:
Email archive is not configured. Run
/add-email-archiveto set up.
Load Configuration
cat /workspace/group/email-accounts.yaml
cat /workspace/group/email-archive/config.yaml
cat /workspace/group/email-archive/rules.yaml
cat /workspace/group/email-archive/state/progress.yaml
Parse into working variables:
- From
email-accounts.yaml: account id, type, address, enabled status - From
config.yaml: archive_accounts (with folder_ids), batch_size, mode, taxonomy, thresholds - From
rules.yaml: sender classification rules - From
progress.yaml: per-account bookmark and stats
Join accounts: for each entry in config.yaml's archive_accounts, look up the account type from email-accounts.yaml.
Provider Operations
Each account in config.yaml has a type field. Use the matching operations:
Type: gws_mcp (Google Workspace via workspace-mcp — recommended)
All operations are MCP tool calls under the mcp__gws_mcp__ prefix. Exact tool signatures are discoverable via MCP at runtime — the names below are the typical ones but may vary with workspace-mcp versions; if a call fails with "unknown tool," list available tools and match by capability.
| Operation | Tool (typical) | Args |
|---|---|---|
| List inbox | mcp__gws_mcp__search_gmail_messages |
query: "in:inbox", max_results: N |
| List with date filter | mcp__gws_mcp__search_gmail_messages |
query: "in:inbox before:YYYY/MM/DD", max_results: N |
| Read message | mcp__gws_mcp__get_gmail_message |
message_id: MSG_ID |
| Move to folder | mcp__gws_mcp__modify_gmail_message_labels |
message_id: MSG_ID, add_labels: [LABEL_ID], remove_labels: ["INBOX"] |
| Batch move | mcp__gws_mcp__batch_modify_gmail_messages |
message_ids: [...], add_labels: [LABEL_ID], remove_labels: ["INBOX"] |
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.
- 11d ago First seen · 314 lines · 77 tokens per session scan A ec597581c92c
email-archive is a skill published in the GitHub repository chiptoe-svg/nanoclaw_flexagents (5 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 2,843 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.