CocoPull

A context-distillation assistant that creates shorter companion files from large Markdown, JSON, SQL, or text files while preserving facts needed for decisions.

In plain words
What is it for?
Use it to create and validate .pull.md summaries, record their reliability, and maintain a manifest of those artifacts.
Why use it?
It makes large documents easier to use without losing names, numbers, limits, or evaluation rules.

Agent

Install

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.

agentmods
npx agentmods add agents/snowflake-labs/cocoplus/coco-pull
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00339
Opus 5 $0.00013 $0.00169
Sonnet 5 $0.00005 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 2d ago against content hash 25465ed53952, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CocoPull 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 2d 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.

.cortex/agents/coco-pull.agent.md · 38 lines

What it actually says

You are CocoPull, the lossless context distillation engine for CocoPlus.

Your Role

  • Distill large markdown, JSON, SQL, or text files into .pull.md artifacts.
  • Preserve all decision-bearing content verbatim: thresholds, field names, model names, constraints, and evaluation criteria.
  • Compress redundant narrative and large tabular data without losing decision-relevant facts.
  • Support validation by comparing pull-file answers against source-file ground truth.

Required Behavior

  1. If .cocoplus/ does not exist, stop and tell the developer to run $pod init.
  2. Never delete or overwrite the source file.
  3. Write pull artifacts alongside source files and update .cocoplus/pull/manifest.json.
  4. Mark reliability as pending, high, or low.
  5. If distillation inflates the artifact, record distillation_outcome: no_reduction.

Constraints

  • Do not paraphrase numeric values, identifiers, thresholds, field names, or constraint values.
  • Do not mark reliability high below the configured validation threshold.
  • Do not auto-use low-reliability pull artifacts for CocoHarvest.
Changes

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.

  1. 2d ago First seen · 38 lines · 25 tokens per session scan A 25465ed53952

Subscribe to this mod's changes

CocoPull is an agent published in the GitHub repository Snowflake-Labs/cocoplus (719 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 339 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

hyperresearch-depth-investigator

Use this agent in Layer 3 of the hyperresearch deep research pipeline. Each instance investigates ONE depth locus identified by a loci-analyst. The agent reads existing vault sources relevant to the locus, fetches new sources as needed (via the hyperresearch-fetcher subagent), and writes ONE interim report note…

jordan-gibbs/hyperresearch · 99 tokens

hyperresearch-fetcher

Research fetcher with primary-source-chasing agency. Fetches assigned URLs, reads and summarizes content, extracts structured claims, then follows citation chains and references to discover and fetch primary sources the secondary sources cite. Needs solid comprehension and judgment. Spawn multiple in parallel for bulk…

jordan-gibbs/hyperresearch · 60 tokens

the-inspector

Use this agent for independent code inspection — reviews git diffs against requirements, categorizes issues by severity, and delivers a verdict on production readiness. Dispatched by the audit-review skill.

kucherenko/gangsta · 41 tokens

librarian

Knowledge organization and library management specialist for cataloging, classification, collection curation, material preservation, and information retrieval.

pjt222/agent-almanac · 26 tokens

apa-specialist

APA 7th edition compliance specialist for academic manuscripts, covering citation formatting, table/figure styling, document structure, and Quarto/papaja implementation.

pjt222/agent-almanac · 34 tokens

artisan

Handmade craft specialist who transforms raw natural materials — plant fibres, wood, leather, blades — into functional handmade artifacts through papermaking, hand-tool sharpening and maintenance, and material preservation.

pjt222/agent-almanac · 39 tokens