agent_stack

A set of three separate agent roles for task tracking, checking parallel work, and maintaining long-running task context. It also documents how these roles connect to project configuration.

In plain words
What is it for?
Use it to configure a taskboard, an output verifier, and J-Space, a system for preserving goals and recovery context across long tasks.
Why use it?
Keeping the roles separate prevents task status, quality checking, and agent memory from being confused with one another.

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/atebites-hub/pjtemplate/agent_stack
Clone the repo
git clone --depth 1 https://github.com/atebites-hub/PJTemplate
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,595 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 $0.00000 $0.01595
Opus 5 $0.00000 $0.00797
Sonnet 5 $0.00000 $0.00319
Haiku 4.5 $0.00000 $0.00160

Measured yesterday against content hash 6fff67563465, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent_stack 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 yesterday.

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.

docs/agents/agent_stack.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent stack — Taskboard, ODW verifier, J-Space

Process doc (not one of the 10 core product documents). One map of three independent layers this template cares about. Record the corresponding decisions in config/setup.toml. Only J-Space is vendored.

Three jobs, three decisions. Do not merge them.

Layer What it decides Setup field In this repo
Coordination (Taskboard) What work happens, card status for sprint items taskboard_plugin Claude plugin marketplace + in-tree skill/hooks; binary on PATH
Orchestration quality (ODW + verifier) Which parallel trajectories are actually good odw_verifier Catalog only — no vendor
Cognition (J-Space) How a long-running model holds goals, seams, and recovery jspace_skill Optional submodule + skill symlink

reasoning-system is not a fourth catalog entry. It is a required project gate (C3 task-memory fields). J-Space does not fill TCREI; reasoning-system does not speak J-Space. They may both run on one task because they write to different places.

Canonical pointers: this file (map), docs/agents/odw_executor_matrix.md (executors), docs/agents/execution_policy.md (when to orchestrate), docs/agents/template_setup_checklist.md §5g–5i (keep/strip / attest), docs/superpowers/specs/2026-08-20-taskboard-plugin-design.md (plugin design).


1. Taskboard (coordination)

Role: a local board for sprint tickets. Not a replacement for ODW scripts (./scripts/odw) and not a replacement for docs/memories/ (C3). Use the board to see ticket status; use memories for reasoning; use ODW when the fan-out must be a rerunnable JS workflow.

config/setup.toml taskboard_plugin: keep | strip

Piece Where
Fork / marketplace atebites-hub/taskboard (upstream tcarac/taskboard, MIT)
Claude plugin taskboard@taskboard via .agents/settings.json
Skill (Cursor/Codex too) .agents/skills/taskboard-workflow/
SQLite .taskboard/taskboard.db (gitignored; never the default Application Support DB)
Binary PATH — brew tap tcarac/taskboard && brew install taskboard or make build in the fork

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 0 tokens per session scan A 6fff67563465

Subscribe to this mod's changes

agent_stack is an agent published in the GitHub repository atebites-hub/PJTemplate (2 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,595 tokens. 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