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 Snowflake-Labs/cocoplus --skill cup-historygit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/cup-history)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/cup-history"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cup-history/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/snowflake-labs/cocoplus/cup-history"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cup-history.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 | $0.00039 | $0.00712 |
| Opus 5 | $0.00019 | $0.00356 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
cup-history 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 7d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to display recent CocoCupper findings.
Before proceeding, verify that .cocoplus/ exists.
If not: output "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Parse argument: $cup history [n] — n defaults to 5.
Read .cocoplus/grove/cupper-findings.md. If it does not exist or is empty:
Output: "No CocoCupper findings yet. Run $cup to trigger an analysis."
Then stop.
Extract the last N findings (each finding starts with ## Finding).
Output each finding in summary format:
| ID | Title | Type | Severity | Date | Promoted |
|----|-------|------|----------|------|----------|
[one row per finding]
Then show the full text of the most recent finding.
Auto-Captured Corrections (Feature 8 Enhancement)
Correction detection is requested silently on every developer prompt via the UserPromptSubmit hook appending a cococupper/cupper-capture request to .cocoplus/v2-runtime-requests.jsonl (Tier 1, no LLM, <50ms). The V2-native capture path appends matches to .cocoplus/cupper/auto-captured.json. This section surfaces those alongside the manual findings above.
Read .cocoplus/cupper/auto-captured.json if it exists. For each auto-captured correction, apply a routing classification:
- incorrect-behavior — the correction reverses or contradicts an action just taken
- missing-variant — the correction asks for an option or mode that didn't exist
- agent-misapplication — the correction indicates a skill or persona was invoked in the wrong context
Output a second table:
| Timestamp | Correction Text | Routing | Skill Context |
|-----------|-----------------|---------|----------------|
[one row per auto-captured entry]
Output: "Showing [N] of [total] findings and [M] auto-captured corrections. Use $patterns promote [finding-id] to promote a finding to the pattern library. Use $wisdom route to route auto-captured corrections to skill edits."
Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|---|---|
| Show all findings regardless of N argument | The N limit exists to prevent overwhelming output in long-running projects with many findings |
| Skip showing the full text of the most recent finding | The summary table alone loses detail — the most recent finding needs full context for action |
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.
- 7d ago First seen · 64 lines · 39 tokens per session scan A ff6e28b5c250
cup-history is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 712 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
task-dependency-patterns
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
factory-triage
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage.
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
herdr-kit-workflows
Set up and operate Herdr Kit safely: install and configure the plugin and Mastra Code integration, manage Review and Work repository scope, open primary repository workspaces, synchronize managers, materialize or dematerialize managed worktrees, and update Herdr Kit settings or shortcuts.
herdr-manager-query
Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed remote-only Review Manager records through the plugin's stable public CLI.
factory-complete-issue
Mark a GitHub issue as done and update its status labels.