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 philipyaz/cos --skill mail-to-boardgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/mail-to-board)<a href="https://agentmods.dev/skills/philipyaz/cos/mail-to-board"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/mail-to-board/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/philipyaz/cos/mail-to-board"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/mail-to-board.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 | $0.00128 | $0.08020 |
| Opus 5 | $0.00064 | $0.04010 |
| Sonnet 5 | $0.00026 | $0.01604 |
| Haiku 4.5 | $0.00013 | $0.00802 |
Grade A, and why
mail-to-board scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
through the **`board`** MCP, never `bash`/`curl` — Cowork's sandbox blocks outbound How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mail → Board (the email reconciler)
This skill reconciles Gmail with the board. For every thread — received and
sent — it links the message onto the right case, closes or adds tasks, moves the
lane, sets labels, and keeps one card per matter. It writes to the board only
through the board MCP, never bash/curl — Cowork's sandbox blocks outbound
HTTP, and the MCP tools exist for exactly this.
The skill does not send or draft email. The only thing it ever writes back to
Gmail is the cos/processed watermark label. And it owns the board side only:
the knowledge in an email — a fact, a decision, new context about the sender — is
submitted to the vault through the vault MCP's async ingest, driven per
/vault-operations; the vault synthesizes knowledge, this skill reconciles cases.
(The vault is knowledge-only: never write task checkboxes into wiki pages — open work
lives on the board.)
The headline guardrail. The board is a shared surface — the human edits it by hand in the UI, the agent edits it through this skill. An email can make the agent think a matter is open that the user has already closed by hand. The agent must never undo a manual action. Step 6 is that contract; read it before any write.
Two companion files carry the depth this workflow points to, so keep this file lean:
references/case-management.md— the full board surface (every lane, field, andboardtool, with when to reach for each). Consult it when you need a tool you don't touch every sweep.references/worked-examples.md— six worked scenarios (respecting a human lane, a sent reply, an apparent reopen, a reminder-not-a-case, prompt injection, a released false-positive). Read it when a thread doesn't fit the common cases below.
Throughout, <BOARD_URL> is your board's base URL — default
http://localhost:3000, from config/cos.env (shell steps resolve it via the loader).
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.
- 12d ago First seen · 441 lines · 128 tokens per session scan A 523faacc6b4e
mail-to-board is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 8,020 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
decision-consolidate
Consolidate a SETTLED decision page (accepted / superseded / rejected — never proposed): compress the body to canon (verdict byte-intact, minimal why, alternatives as a table) and move the deliberation chronicle to a verified archives/ note (type: decision-archive) excluded from recall and search. Compress + archive…
fizzy-tasks
Fetch open Fizzy cards assigned to the user, open bugs, and unassigned tasks. Presents a prioritised digest with deep links. Use when user says "fizzy tasks", "my fizzy cards", "what are my open tasks in fizzy", "fizzy action items", "bugs in fizzy", "show my tasks", or wants a digest of current Fizzy workload.
fizzy-write
Create cards, create boards, update cards, close/reopen cards, add comments, assign users, or move cards to a column in Fizzy. Use when user says "create card", "create board", "add task to fizzy", "close fizzy card", "comment on fizzy card", "assign fizzy card", "move card to column", or anything involving writing to…
fizzy-board-monitor
Show an on-demand Kanban overview of a Fizzy board — cards grouped by column with counts. Default board is the QA board. Use when user says "show fizzy board", "fizzy board overview", "list fizzy cards", "what's on the board", "show [board name] board", or wants to see the current state of any Fizzy board.
fizzy-product-manager
Product management knowledge for Fizzy Kanban boards — Kanban principles, API workflows, triage, hygiene, and reporting.