A repository-local system for organizing work as a task forest, which is a set of related tasks connected by parent-and-child relationships. It tracks proposals, history, progress, deviations, and outstanding items in a standalone HTML report.

Use it to initialize or update a task forest, close a work session, summarize project progress, align requests with larger goals, save or apply task proposals, and export a readable report.

Project work can become difficult to follow when tasks, dependencies, and past decisions are scattered across files or sessions. This keeps that evolving structure in one portable record.

task-forest — Skill for Codex by dongshuyan

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.

Any agent

npx skills add dongshuyan/compass-skills --skill task-forest

Clone the repo

git clone --depth 1 https://github.com/dongshuyan/compass-skills

Made for: Codex.

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/skills/dongshuyan/compass-skills/task-forest/github.svg)](https://agentmods.dev/skills/dongshuyan/compass-skills/task-forest)

Your own site

<a href="https://agentmods.dev/skills/dongshuyan/compass-skills/task-forest"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/task-forest/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/skills/dongshuyan/compass-skills/task-forest"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/task-forest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,376 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 22
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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	$0.00090	$0.01376
Opus 5	$0.00045	$0.00688
Sonnet 5	$0.00018	$0.00275
Haiku 4.5	$0.00009	$0.00138

Measured 9d ago against content hash dbcf83b78596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-forest 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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/task_forest_html.py, scripts/task_forest_ordering.py, scripts/task_forest.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/task-forest/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Forest

Purpose

Maintain the current workspace's task structure, proposals, history, and progress. Produce one standalone HTML deliverable that a first-time reader can understand without opening another task list or internal file.

Use the user's language for task content, proposals, reports, and HTML. Default to Chinese when unknown.

Portability

This skill is agent-agnostic. Install the whole task-forest directory in any host-supported skill location, then resolve scripts, references, and assets from the directory containing this SKILL.md. Do not assume a specific agent name, skill root, home-directory layout, shell, path separator, or operating system.

Use an available Python 3 launcher on the host (python3, python, or py -3). The scripts use the Python standard library and support macOS, Linux, and Windows. To label task history with the calling agent, set COMPASS_AGENT_NAME or AGENT_NAME, or pass --actor; otherwise the neutral value agent is used.

Core Rules

Read and write task-forest data only through scripts/task_forest.py; never hand-edit .agent-workbench/task-forest/ canonical files.
Use one primary child_of parent per node, contributes_to for secondary ownership, and depends_on for prerequisites.
Save graph changes as a proposal and wait for user confirmation before proposal-apply --yes.
Keep low-confidence inference in a question or proposal. Record material execution drift as a deviation.
Write visible task titles and purposes in plain language. A reader must understand what the task delivers, why it exists, and what has been completed without knowing internal codes such as P04 or reading another file.
Export one HTML surface: exports/task-forest.html. It shows done, in_progress, and their necessary child_of ancestors, with history playback. Do not expose internal discussions, evidence, queues, filesystem paths, sessions, or proposal content in the HTML.
Keep HTML interactions read-only. Formal changes always return through the proposal workflow.
Keep task data and discovery metadata repo-local by default. Cross-workspace discovery is optional: enable it only after the user explicitly opts in by setting TASK_FOREST_ENABLE_GLOBAL_REGISTRY=1. This writes lightweight workspace paths and health summaries to AGENT_WORKBENCH_DB, or to ~/.agent-workbench/agent-workbench.sqlite3 when that variable is unset; it never stores task content.

Read the full file on GitHub · 99 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 99 lines · 90 tokens per session scan A dbcf83b78596

Subscribe to this mod's changes

task-forest is a skill published in the GitHub repository dongshuyan/compass-skills (724 stars, last pushed 13d ago), licensed MIT. It adds 90 tokens to every session and 1,376 once invoked, about $0.0005 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.

Claude Code Planning Project management agent-memory agent-skills ai-agents ai-coding-agent claude-skills

fleet-conductor

Use when conducting a large backlog or multi-repository campaign across several worker lanes, especially when work needs bounded ownership, held dependencies, collision control, draft pull request gates, and evidence-based landing. Triggers on "conduct the fleet", "burn down the backlog", "run a multi-repo campaign"…

escoffier-labs/skillet · 73 tokens

task-forest

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Task Forest

Purpose

Portability

Core Rules

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

fleet-conductor

handoffplan

start

github

lisa

jira