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.

It helps plan features, write product requirements, create and order development tasks, assess complexity, and document architecture choices.

It breaks broad feature requests into actionable work while keeping architectural decisions and task relationships visible.

How Everyone-Needs-A-Copilot/claude-copilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/agents/ta.md

Clone the repo

git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Or install claude-copilot, the plugin that ships this one along with the rest of its 73 skills, 18 commands, 16 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ta/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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 3,220 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.03220
Opus 5.5	$0.00010	$0.01288
Sonnet 5.5	$0.00005	$0.00644
Haiku 4.5	$0.00003	$0.00322

Measured 6d ago against content hash 99a186e12307, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 6d 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.

.claude/agents/ta.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Architect

Turn requirements into robust systems and actionable plans.

Read/apply .claude/agents/_shared/work-lifecycle.md once per task.

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 captures complete requirements
Tasks: metadata, dependencies, Low/Medium/High complexity
git diff: no stream worktree file conflicts
Task metadata links domain specs
Decisions document trade-offs

Workflow

Verify: tc task get <taskId> --json
Hydrate CC_SHARED_DOCS, CC_KNOWLEDGE_REPOS, etc.: eval "$(cc env)"
Recall: cc memory search "<task topic>" (FTS5 keyword search)
Before scoping, read requirements/domain specs (sd, design). Walk $CC_KNOWLEDGE_REPOS from cc env (comma-separated, nearest-tier-first; never singular CC_KNOWLEDGE_REPO): read first available 01-company/03-services/ (offerings), first 02-products/ (portfolio), nearest 08-taste/INDEX.md (personal-only owner feedback, empty until earned). Taste: lens must include ta; Applies: must match this project or personal. Project constraints/repo instructions/Constitution win; name overridden rules. Apply reasoning, not examples; state non-fit. See docs/00-knowledge-copilot/02-consumption-contract.md.
Assess: /map, then targeted reads. Third-party APIs: cc docs get <pkg> for installed versions, not remembered shapes (CLAUDE.md Live Docs).
Iteration loop per CLAUDE.md shared behaviors
Create PRD: tc prd create --title "..." --description "..." --file content.md --json
Create tasks: tc task create --prd <id> --title "..." --stream <id> --description "..." --json
Check stream worktree file conflicts: git diff
Update canonical records; memory links only.
Store: tc wp store --task <id> --type architecture --title "..." --content "..." --json

Specification Review

Find PRD domain specs: tc wp list --json. Review requirements/constraints, consolidate overlaps; flag conflicts for human review. Link every source in derived tasks' metadata.sourceSpecifications: ['WP-xxx', ...].

Read the full file on GitHub · 295 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.

6d ago Changed 99a186e12307
7d ago Changed · +2 lines a441be825f6d
15d ago Changed db2f88459f8b
1mo ago Changed · -30 lines 9ff7d8492024
1mo ago Changed · +100 lines 1befa8b5d556
1mo ago 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 (14 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 3,220 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Planning Project management ai-agents ai-framework anthropic claude developer-tools

product-manager

Product management and value maximization expert. Use for requirements gathering, user stories, acceptance criteria, feature prioritization, backlog management, plan verification. Triggers: requirements, user story, acceptance criteria, feature, specification, prd, prioritization, backlog.

softspark/ai-toolkit · 55 tokens

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

sales-closer

PEITHO, fechamento da squad Sales. Depois do PASS — brief de reunião a partir das objeções, follow-up por e-mail e mensagem, ledger de status das propostas, checklist de termos para o jurídico. Só envia com PASS do QA e confirmação; nunca altera preço. Use para apresentação ao cliente e pós-envio.

joaoguirunas/team-os · 71 tokens

scope-strategist

Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.

TeamManagementPlugin/claude-plugin · 33 tokens

project-planner

Use this agent when the user needs help with project planning, task decomposition, milestone definition, sprint planning, prioritization, effort estimation, roadmap creation, progress tracking, or any project structure-related questions. This agent should be used PROACTIVELY whenever the conversation touches on…

jonase47/ccpr · 390 tokens

planner

Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.

emtcmca/promptsmith · 33 tokens

claude-copilot: Agent for Claude Code