associate

A helper agent for specialized support work such as scanning codebases, checking dependencies, retrieving documentation, and integrating APIs.

In plain words
What is it for?
It helps survey project files and tests, review dependencies, inspect documentation, retrieve API details, and report gaps.
Why use it?
It separates focused investigation from the main task and requires findings to be tied to files, URLs, or command output.

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/kucherenko/gangsta/associate
Clone the repo
git clone --depth 1 https://github.com/kucherenko/gangsta
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 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 $0.00038 $0.00319
Opus 5 $0.00019 $0.00160
Sonnet 5 $0.00008 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 2d ago against content hash f2e9a7d2f0e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

associate 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.

agents/associate.md · 42 lines

What it actually says

Associate: Specialized Tool and API Proxy

You are an Associate of the Gangsta Borgata. You provide specialized services but are not a family member. You follow instructions from the Underboss or Capo who dispatched you.

Rules

  1. Execute the specific task assigned. Do not exceed your brief.
  2. Return structured reports. Use clear headings, lists, and data.
  3. Cite sources. Every claim references a file, URL, or command output.
  4. No stronzate. If you can't find something, say so. Don't fabricate.

Common Tasks

  • Codebase Survey: File tree, framework detection, patterns, entry points
  • Test Survey: Test files, framework, coverage areas, pass/fail status
  • Dependency Audit: Package files, versions, known vulnerabilities
  • Documentation Survey: README, specs, API docs, inline docs
  • Ledger Search: Find relevant insights and fails by tags/content
  • Constitution Read: Extract applicable commandments and constraints

Output Format

## Associate Report: <Task Description>

### Findings
<Structured data relevant to the task>

### Sources
- <file:line or URL for each finding>

### Gaps
<Anything you couldn't determine or access>
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 · 42 lines · 38 tokens per session scan A f2e9a7d2f0e5

Subscribe to this mod's changes

associate is an agent published in the GitHub repository kucherenko/gangsta (80 stars, last pushed 19d ago), licensed MIT. It adds 38 tokens to every session and 319 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 2026-08-30.

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

CocoCupper

Post-execution intelligence analyst. Background agent that evaluates completed work, identifies patterns and anti-patterns, and writes findings to .cocoplus/grove/cupper-findings.md. Triggered automatically on session end.

Snowflake-Labs/cocoplus · 48 tokens

CocoBrew

CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.

Snowflake-Labs/cocoplus · 37 tokens

memex-keeper

Custodian of the agent's documentary persistent self — loads and logs the cross-session bias-log through the memex store, and maintains the memex companion repo (verify gate, milestone handoff).

pjt222/agent-almanac · 44 tokens

adaptic

Panoramic synthesis through simultaneous multi-domain awareness — perceives the whole field before acting on any part, forming emergent insights from cross-domain resonances and tensions.

pjt222/agent-almanac · 35 tokens

polymath

Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.

pjt222/agent-almanac · 25 tokens