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 instructions/snowflake-labs/cocoplus/agents-mdgit 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/instructions/snowflake-labs/cocoplus/agents-md)<a href="https://agentmods.dev/instructions/snowflake-labs/cocoplus/agents-md"><img src="https://agentmods.dev/badge/instructions/snowflake-labs/cocoplus/agents-md.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 | $0.02470 | $0.02470 |
| Opus 5 | $0.01235 | $0.01235 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
cocoplus AGENTS.md 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 5d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CocoPlus Plugin — Behavioral Rules
Auto-loaded by Coco when CocoPlus plugin is active.
This is the plugin-level AGENTS.md.
Per-project context lives in .cocoplus/AGENTS.md after $pod init.
Plugin Identity
You have the CocoPlus plugin active. CocoPlus enhances Coco with:
- CocoBrew lifecycle engine ($spec, $plan, $build, $test, $review, $ship)
- CocoHarvest parallel workstream decomposition ($harvest)
- Specialist Personas ($de, $ae, $ds, $da, $bi, $dpm, $dst, $cdo)
- Safety Gate SQL protection ($safety strict/normal/off)
- Memory Engine cross-session persistence ($memory on/off)
- Environment Inspector Snowflake state snapshot ($inspector on/off)
- CocoFlow pipeline execution ($flow run/status/pause/resume/view)
- SecondEye multi-model plan critic ($secondeye)
- CocoFleet multi-process orchestration ($fleet init/run/status/stop/logs/comms)
- CocoCupper background intelligence analyst ($cup, $cup history)
- CocoGrove pattern library ($patterns view, $patterns promote, $grove glossary)
- Code Quality Advisor SQL/code anti-pattern checker ($quality on/off)
- Prompt Studio prompt engineering & comparison ($prompt, $prompt compare)
- Doc Engine auto-documentation ($doc run)
- Context Mode context transparency ($context-mode on/off)
- CocoMeter token tracking ($meter on/off, $meter, $meter estimate, $meter history)
- CocoMeter Enhanced flow attribution & dashboard ($meter view, $meter sync, $meter accuracy)
- CocoView flow pipeline visualizer ($flow view)
- Assist Mode master feature toggle ($cocoplus on/off)
- CocoContext organizational standards capture ($context add, $context view, $context list)
- CocoBehavior ambient behavioral constraints (auto-loaded by all personas)
- CocoScout relevance-ranked context loading (automatic pre-execution)
- CocoMap Cortex function knowledge graph ($map, $map diff, $map explain)
- CocoRecipe pre-built pipeline templates ($recipe list, $recipe use, $recipe new)
- CocoDream supervised cross-session pattern distillation ($dream, $dream history)
- CocoSeed deferred ideas with trigger conditions ($seed add, $seed list, $seed promote)
- CocoDiscuss decision-locking pre-plan phase ($discuss)
- CocoLens HITL/AFK task classification (integrated into CocoHarvest decomposition)
- CocoWatch developer engagement observer (non-blocking, surfaces at $ship)
- CocoHealth context utilization monitor (automatic via PostToolUse hook)
- CocoBloom working-backwards pre-commitment gate ($bloom, $bloom --skip)
- CocoKlatch genuine multi-agent roundtable ($klatch, $klatch --participants=N)
- CocoPull lossless context distillation ($pull, $pull --validate)
- CocoSentinel eight-dimension artifact quality gate ($sentinel, $sentinel approve, $sentinel --report)
- CocoWisdom institutional rejection memory ($wisdom, $wisdom list, $wisdom search, $wisdom insights)
- CocoReview structured code review with six-severity vocabulary ($review, $review --security, $review --complexity)
- CocoOps delivery intelligence dashboard ($ops dora, $ops sprint, $ops suggest, $ops demo)
- CocoConsole V2 read-only local browser control plane ($cocoplus console)
- CocoPilot V2 natural-language orchestration mode ($pilot on/off)
- CocoForge V2 goal-driven expert-team loop ($forge, $forge goal/status/stop)
- Leviathan + Ronin V2 explicit-activation autonomous coordination ($leviathan on/off/status/learn)
- Dynamic Personas V2 evidence-gated emergent specialists ($personas discover/list/invoke/dissolve)
- Governance Hooks V2 ReviewerLockout and PII governance observe/enforce policies
- CocoSession V2 multi-session continuity and operator control ($session status/progress/steer/stop/resume)
- CocoFlow Evidence and Proposal Gates V2 opt-in stage evidence and retained proposal settlement ($flow settle)
- CocoRetro and CocoHygiene V2 measured improvement loops ($retrospective, $hygiene --model-upgrade, $meter benchmark)
- CocoRoutine V2 opt-in Snowflake TASK scheduling for self-contained completed workflows ($routine)
- Late-Cycle Governance and Quality Gates V2 RBAC escalation guard, bypass safeguard logging, named artifacts, stage coach, correctness-first metering, allowlisted transcript adapter, run-policy snapshots, inbox-first stage transitions, critic read-only separation, timestamp provenance, complexity-aware dispatch, ACRR calibration, and CocoBrew distribution gate
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.
- 5d ago First seen · 145 lines · 2,470 tokens per session scan A 5688e47f3623
cocoplus AGENTS.md is an instructions file published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 2,470 tokens to every session, about $0.0123 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 2026-08-30.
Other instructions, from other repositories
mcp-server-snowflake AGENTS.md
AGENTS.md instructions for christianclaudio/mcp-server-snowflake, covering agents.md, project overview, architecture, development commands and install editable with dev dependencies.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).