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 agentmods add skills/snowflake-labs/cocoplus/plannpx skills add Snowflake-Labs/cocoplus --skill plangit 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/plan)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/plan"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/plan.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 | $0.00063 | $0.01653 |
| Opus 5 | $0.00032 | $0.00826 |
| Sonnet 5 | $0.00013 | $0.00331 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
plan 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 yesterday.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are executing the Plan phase (2/6) of CocoBrew. Your objective is to transform the approved specification into an executable plan.
Before proceeding, verify that .cocoplus/ exists in the current directory.
If it does not, output: "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Read .cocoplus/lifecycle/meta.json. Verify phases_completed contains "spec".
If not: output "The Spec phase must be completed before planning. Run $spec to capture requirements first." Then stop.
CocoSpec Pre-Flight Quality Gate
Before entering plan mode, run the CocoSpec scoring gate. Spawn a background Haiku subagent (read-only) to score spec.md and discuss.md (if it exists) against five dimensions:
| Dimension | Score 0 | Score 1 | Score 2 |
|---|---|---|---|
| Value | No rationale | Rationale present but benefits not measurable | Clear rationale with verifiable success metrics |
| Scope | No scope definition | MVP defined but out-of-scope not stated | Both MVP and explicit out-of-scope defined |
| Acceptance | No acceptance criteria | Criteria stated but not testable | Testable criteria with clear pass/fail determination |
| Boundaries | None addressed | Partial coverage | All four (error handling, performance, compatibility, security) addressed |
| Risk | No risk assessment | Risks identified but no mitigation | Risks identified with explicit mitigation or escalation plan |
The scoring agent writes the score and per-dimension rationale to lifecycle/spec-score.md.
Gate behavior:
- Score ≥9: Gate passes. Check Quick Mode eligibility (see below).
- Score 8: Hold. Show which dimension scored below 2. Ask developer to address the gap before proceeding.
- Score ≤7: Hold. Output an Uncertainty Declaration for every sub-2 dimension — name each assumption being made rather than stated. Developer must address before planning proceeds.
Uncertainty Declaration format (for score ≤7):
UNCERTAIN: [dimension description] | ASSUMPTION: [what is being assumed]
Quick Mode check (score ≥9 only): If score ≥9 AND spec scope is ≤3 files (detectable from spec.md's Deliverables section) AND no EHRB indicators in the planned operations: offer Quick Mode — "Your specification qualifies for Quick Mode. Skip Plan phase and proceed directly to Build?" Quick Mode requires explicit developer confirmation. If accepted, record "quick_mode": true in lifecycle/meta.json and add "plan" to phases_completed with a note, then skip to Build.
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.
- yesterday First seen · 166 lines · 63 tokens per session scan A b260edbb0963
plan is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,653 once invoked, about $0.0003 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
prompt-engineering
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
initialize
First-run setup interview for a Danus deployment. Run it on the FIRST session, whenever runtime/.danus-initialized is absent or OPERATOR.md is still the blank template, or when the operator asks to set up / initialize / onboard / re-configure. It greets the operator, explains Danus, asks the critical choice (codex…
playground-msw-tests
REQUIRED and PRIMARY testing approach for packages/playground and packages/playground-ui. Triggers on: adding or modifying hooks, pages, route components, data-fetching code, React Query interactions, or any test work in these packages. Generates Vitest tests that drive the real @mastra/client-js + React Query stack…
cron
Schedule, list, pause, resume, edit, or run the user's agentica cron jobs with the cronjob tool. Use when asked to remind, schedule a recurring or one-shot task, try a job now, or manage jobs that fire unattended.