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 board-organizegit 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/board-organize)<a href="https://agentmods.dev/skills/philipyaz/cos/board-organize"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/board-organize/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/board-organize"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/board-organize.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 | $0.00208 | $0.08184 |
| Opus 5 | $0.00104 | $0.04092 |
| Sonnet 5 | $0.00042 | $0.01637 |
| Haiku 4.5 | $0.00021 | $0.00818 |
Grade A, and why
board-organize 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 6d 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.
the board **only** through the **`board`** MCP — never `bash`/`curl` (Cowork's How it starts
The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Board → Organize (the hierarchy housekeeper)
This skill reorganizes the existing board into a clean three-tier tree. The
reconcilers (/mail-to-board, /whatsapp-triage) deliberately create every new
matter as a flat standalone case — one clean card per matter — and leave the
structure to this sweep. This skill is the only owner of hierarchy: it clusters
related cases under Initiatives, splits a grown Initiative into Workstreams,
dedups duplicate containers, and keeps the user's priorities visible. It writes to
the board only through the board MCP — never bash/curl (Cowork's
sandbox blocks outbound HTTP; the tools exist for exactly this).
It owns only the shape of the tree — kind, parentId, container lifecycle,
and the title / summary of the containers it created (so it can rename a
sloppy Initiative to the canonical entity name and give it a one-line description).
It does not triage messages, create cases from channels, move lanes, add/close
tasks, set labels, edit a case's body, or send anything. Reconciliation is the
reconcilers' job; knowledge is the vault's job (the reconcilers submit it via
/vault-operations); this skill files and labels the structure of what already
exists.
The sweep also runs a weekly staleness lens (cos-ops#24) — the one deliberate
exception to "never touch tasks / events": it ranks the board's most-starved
obligations, fills a researched next step into a starving case's task
(detail/dueAt), and places one linked timed chase block. It still never
triages messages, moves lanes, sets labels, or sends anything — see STEP 7.
Guardrail 1 — the human's hand wins. The board is a shared surface. Never re-home a node a human placed by hand. Only an
agent-placed or never-placed case is yours to move; a human'sparentIdis frozen, exactly like any other manual edit. STEP 3 is the contract — read it before anyset_parent/regroup_cases.
Guardrail 2 — never bury or drop a priority. A starred node, a
P0/P1case, or a case named by a priority note is pinned intent. Surface it, anchor Initiatives on it, keep it shallow — and neverarchive_casea starred node (archiving silently drops it off the Priorities surface even though the star is still set). STEP 1 grounds the whole sweep inget_priorities.
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.
- 6d ago Changed · +28 lines 84658ccd4aa6
- 10d ago First seen · 488 lines · 208 tokens per session scan A 2364284f9748
board-organize is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 208 tokens to every session and 8,184 once invoked, about $0.0010 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-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-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-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.