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 lean-debtgit 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/lean-debt)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/lean-debt"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/lean-debt.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01378 |
| Opus 5 | $0.00019 | $0.00689 |
| Sonnet 5 | $0.00008 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
lean-debt 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are executing $lean debt — the CocoLean shortcut debt ledger. Harvest all cocoplus: comment markers across the CocoPod, assess ceiling imminence, and produce a ranked deferral report. Run this before sprint planning and before any release gate.
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus is not initialized. Run $pod init first." Then stop.
Step 1 — Run Deterministic Marker Harvest
invoke cocolean/lean-debt-engine
Run the command directly with Node. Do not wrap it in PowerShell redirection such as 2>&1; stderr handling differs across shells and can corrupt the JSON output.
The script:
- Scans all
.sql,.js,.md,.yaml,.jsonfiles in the CocoPod forcocoplus:comment markers - Extracts the three required fields from each marker: what was simplified, ceiling condition, upgrade trigger
- Calculates ceiling imminence from current project metrics (from
dora-snapshot.json,flow.json,meta.json) - Outputs a JSON array of debt records sorted by
(ceiling_imminence × days_since_annotation)
Read the JSON output.
Step 2 — The cocoplus: Comment Protocol
A valid cocoplus: marker looks like this:
-- cocoplus: simplified=single-warehouse routing; ceiling=will fail when concurrent agent count >20; trigger=when $build spawns >20 agents in one run
// cocoplus: simplified=linear scan for seed matching; ceiling=scan time exceeds 5s above 500 seeds; trigger=when $seed list reports >500 entries
Three required fields (pipe-delimited or semicolon-delimited):
simplified=— one sentence describing the shortcut taken and whyceiling=— the condition under which this shortcut fails or requires reworktrigger=— the specific event that should prompt addressing the ceiling
Markers missing any required field are reported as malformed but not blocked.
Step 3 — Produce Ranked Deferral Report
Write the report to .cocoplus/lifecycle/lean-debt.md and display a summary. The summary must include a compact dashboard table grouped by imminence and a trigger surface listing the next concrete events that would force 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.
- 4d ago First seen · 153 lines · 0 tokens per session scan A 4c77cbd62221
lean-debt is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,378 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
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…
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.
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.