teds-initializer

An agent for starting a TEDS task. TEDS, or Task Execution Documentation System, is a way to organize long-running work with plans, status records, logs, and learning notes.

In plain words
What is it for?
Use it when beginning a substantial task that needs a named task record, an execution plan, success criteria, and ongoing documentation.
Why use it?
It creates the documentation structure needed to track a task over time instead of keeping decisions and progress scattered.

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/legacybridge-tech/claude-plugins/teds-initializer
Clone the repo
git clone --depth 1 https://github.com/legacybridge-tech/claude-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,262 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 $0.00010 $0.03262
Opus 5 $0.00005 $0.01631
Sonnet 5 $0.00002 $0.00652
Haiku 4.5 $0.00001 $0.00326

Measured 2d ago against content hash ab1bd49d25f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teds-initializer 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.

teds/agents/teds-initializer.md · 603 lines

How it starts

The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TEDS Task Initializer Agent

You are initializing a new long-term task using TEDS (Task Execution Documentation System).

Load Configuration

First, determine workspace location:

  1. Check CLAUDE.md:

    if test -f "CLAUDE.md"; then
      grep -A 2 "## TEDS Configuration" CLAUDE.md | grep "Workspace Directory" | sed 's/.*`\([^`]*\)`.*/\1/'
    fi
    
  2. Check .teds-config.yaml:

    if test -f ".teds-config.yaml"; then
      grep "path:" .teds-config.yaml | awk '{print $2}'
    fi
    
  3. Error if neither exists:

    ❌ TEDS not initialized in this project.
    
    Please run: /teds-init
    

Store workspace path as WORKSPACE for all subsequent operations.

Parse User Input

From the command: /teds-start task-name [optional-description]

Extract:

  • TASK_NAME: Clean name (lowercase, hyphens, no spaces)
  • DESCRIPTION: User-provided description or prompt for it

Validation:

# Check task name
[[ ! "$TASK_NAME" =~ ^[a-z0-9-]+$ ]] && echo "ERROR: Name must be lowercase letters, numbers, and hyphens only"
[[ ${#TASK_NAME} -gt 50 ]] && echo "ERROR: Name too long (max 50 chars)"

Generate Task ID

Format: YYYYMMDD-HHMM-taskname

TASK_ID="$(date +%Y%m%d-%H%M)-${TASK_NAME}"

Example: 20250116-1430-refactor-auth

Check for conflicts:

if test -d "${WORKSPACE}/active_tasks/${TASK_ID}"; then
  echo "ERROR: Task ID already exists (rare timing collision)"
  # Suggest: Wait a minute and try again, or use different task name
fi

Create Directory Structure

TASK_DIR="${WORKSPACE}/active_tasks/${TASK_ID}"

mkdir -p "${TASK_DIR}"

Verify:

test -d "${TASK_DIR}" || echo "ERROR: Failed to create task directory"
test -w "${TASK_DIR}" || echo "ERROR: Task directory not writable"

Initialize Documentation Files

Create all required files with templates:

1. manifest.yaml

task_id: {TASK_ID}
name: {TASK_NAME}
description: {DESCRIPTION}
created_at: {ISO_TIMESTAMP}
completed_at: null
status: active
workspace: {WORKSPACE}
version: 1.2.0
tags: []

Read the full file on GitHub · 603 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. 2d ago First seen · 603 lines · 10 tokens per session scan A ab1bd49d25f3

Subscribe to this mod's changes

teds-initializer is an agent published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 3,262 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens