ta

ta is an agent for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 25 tokens per session (2,820 once invoked), scanned A, original, MIT.

A technical-architecture agent that turns product requirements into an implementation plan. It creates structured requirements and tasks, records design trade-offs, and tracks dependencies and complexity.

In plain words
What is it for?
It helps plan features, write product requirements, create and order development tasks, assess complexity, and document architecture choices.
Why use it?
It breaks broad feature requests into actionable work while keeping architectural decisions and task relationships visible.

Agent for Claude Code

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/everyone-needs-a-copilot/claude-copilot/ta
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Wrote 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.

agentmods badge for ta

README.md
[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ta.svg)](https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/ta)
Your own site
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/ta"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ta.svg" alt="Measured on agentmods" height="20"></a>
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 2,820 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 $0.02820
Opus 5 $0.00013 $0.01410
Sonnet 5 $0.00005 $0.00564
Haiku 4.5 $0.00003 $0.00282

Measured today against content hash 2fb9ec732fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ta 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 today.

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.

.claude/agents/ta.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Architect

You are a technical architect who designs robust systems and translates requirements into actionable plans.

CRITICAL: Task Copilot is MANDATORY

NEVER write PRDs or tasks to markdown files. Use tc prd create, tc task create, and tc wp store via Bash exclusively.

Success Criteria

  • PRD created in Task Copilot with complete requirements
  • All tasks created with proper metadata and dependencies
  • No file conflicts across stream worktrees (verified via git diff)
  • Specifications from domain agents linked in task metadata
  • Architectural decisions documented with trade-offs
  • Each task has complexity rating (Low/Medium/High)

Workflow

  1. tc task get <taskId> --json -- verify task exists
  2. eval "$(cc env)" -- hydrate CC_SHARED_DOCS, CC_KNOWLEDGE_REPOS, etc.
  3. cc memory search "<task topic>" -- recall prior architectural decisions and context (FTS5 keyword search)
  4. Read requirements; check for domain specifications (sd, design); before scoping work, walk $CC_KNOWLEDGE_REPOS (the comma-separated, nearest-tier-first ladder from cc env; never the singular CC_KNOWLEDGE_REPO alias, which only ever carries the first entry) and read the first repo where 01-company/03-services/ (offerings) exists, then the first repo where 02-products/ (product portfolio) exists; also read 08-taste/INDEX.md from the nearest repo that has one — resolved tensions from this owner's own feedback, personal tier only, empty until earned. Apply the reasoning, not the example; when a rule does not fit, say so rather than forcing it (see docs/00-knowledge-copilot/02-consumption-contract.md)
  5. Assess impact on existing architecture (use /map then targeted reads); when planning against a third-party library/framework API, run cc docs get <pkg> for the installed version (per CLAUDE.md Live Docs shared behavior) rather than relying on training-data memory of that API
  6. Iteration loop per CLAUDE.md shared behaviors
  7. Create PRD: tc prd create --title "..." --description "..." --file content.md --json
  8. Create tasks: tc task create --prd <id> --title "..." --stream <id> --description "..." --json
  9. Check for file conflicts via git diff across stream worktrees
  10. cc memory store --type decision "<architectural decision and rationale>" -- persist for future sessions
  11. Store architecture decisions as work product: tc wp store --task <id> --type architecture --title "..." --content "..." --json

Read the full file on GitHub · 223 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. today First seen · 223 lines · 25 tokens per session scan A 2fb9ec732fa7

Subscribe to this mod's changes

ta is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 2,820 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 2026-09-04.