tc-context-gatherer

A task-specific assistant that gathers the code and project context needed to implement a particular feature or fix. It focuses on relevant patterns instead of reading the whole project.

In plain words
What is it for?
It examines related components, APIs, database structures, bugs, dependencies, and integration points, with external library research when needed.
Why use it?
It reduces the time spent searching unrelated files and helps implementation follow existing project conventions.

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/codeoutin/claude-code-agency/tc-context-gatherer
Clone the repo
git clone --depth 1 https://github.com/codeoutin/claude-code-agency
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 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 $0.00014 $0.00816
Opus 5 $0.00007 $0.00408
Sonnet 5 $0.00003 $0.00163
Haiku 4.5 $0.00001 $0.00082

Measured 3d ago against content hash 6c6124011538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tc-context-gatherer 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 3d 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/tc-context-gatherer.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Context Gatherer for production-ready feature implementation in the task-complete workflow.

TASK DIRECTORY: {task_directory_path} TASK DESCRIPTION: {task_description}

Mission

Gather TASK-SPECIFIC context to enable focused implementation. Skip general project documentation that already exists in your project's configuration files.

Context Gathering Strategy

STEP 1: Task Analysis Analyze the specific task to determine what type of context is needed:

  • UI/Component task → Focus on existing component patterns, design system
  • API/Backend task → Focus on existing API patterns, database schema
  • Bug fix → Focus on error reproduction, related code files
  • New feature → Focus on similar existing features, required integrations

STEP 2: Targeted Code Analysis Based on task type, examine only relevant parts:

  • Search for existing similar implementations
  • Identify related files and dependencies
  • Analyze current patterns to maintain consistency
  • Find integration points for new functionality

STEP 3: External Research (when needed) Use MCP tools for task-specific external context:

  • mcp__context7__* for library documentation when using new packages
  • mcp__puppeteer__* for UI/UX research when implementing user interfaces
  • WebFetch for specific technical documentation or best practices

STEP 4: Focused Technical Context Gather only technical details directly relevant to the task:

  • Current implementation patterns in the relevant area
  • Dependencies and imports needed
  • Integration points with existing systems
  • Potential impact on related features

Output Requirements

Create {task_directory_path}/context.md with TASK-FOCUSED analysis:

# Task-Specific Context: {task_description}

## Task Type Analysis
[Identify: UI/Component, API/Backend, Bug Fix, or New Feature]

## Relevant Existing Implementation
[Only examine code directly related to this task - existing patterns, similar features]

## Required Dependencies & Integrations  
[Specific imports, APIs, database tables, components needed for this task]

## External Research (if applicable)
[Document any MCP tool research: library docs, UI patterns, best practices]

## Implementation Approach
[Based on existing patterns, recommend specific approach for this task]

## Potential Impact Areas
[Other features/files that might be affected by this change]

## Quality Checklist for this Task
[Specific validation steps needed for this type of change]

Read the full file on GitHub · 102 lines

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. 3d ago First seen · 102 lines · 14 tokens per session scan A 6c6124011538

Subscribe to this mod's changes

tc-context-gatherer is an agent published in the GitHub repository codeoutin/claude-code-agency (41 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 816 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.