Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one…
Install Task And Project
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-project --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .claude/skills/task-and-project && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .claude/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-projectType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-project --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .agents/skills/task-and-project && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .agents/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-project --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .cursor/skills/task-and-project && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .cursor/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Sidiora-Labs/centra-gideon-agent.git --path runtime/gideon/extensions/skills/bundled/task-and-project--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-project --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .gemini/skills/task-and-project && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .gemini/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-projectInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .github/skills/task-and-project && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .github/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent task-and-project --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/task-and-project .opencode/skills/task-and-project && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "task-and-project" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/task-and-project into .opencode/skills/task-and-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-and-project", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
task-and-project- GitHub stars
- 181
- Token cost
- ~1.1k tokens
- SKILL.md length
- 580 words
- Files
- 1
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one…
- Works in 5 steps: State the outcome in one sentence — what… → Break it into atomic units — each unit… → Map dependencies — which units block… → …
- Tasks that involve Subagents
- SKILL.md covers Tasks — the unit of tracked work, Project decomposition discipline, Goal loops — autonomous… and Parallel work with subagents, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Task And Project is an agent skill from Sidiora-Labs/centra-gideon-agent. Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/task-and-project”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- State the outcome in one sentence — what "done" looks like for the whole
- Break it into atomic units — each unit independently doable and
- Map dependencies — which units block which. Independent units can run in
- Assign an execution mode per unit
- Keep one coherent plan — track units and their state as Tasks so progress
What it can do on your machine
Read from SKILL.md and the folder at commit 2176d5b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Task And Project loads about 1.1k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 580 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Sidiora-Labs/centra-gideon-agent at commit 2176d5b, republished under its Apache-2.0 licence (© Sidiora-Labs). 580 words, ~1,123 tokens.
Download SKILL.mdSave it as
.claude/skills/task-and-project/SKILL.md (or your agent's skills folder).- name
- task-and-project
- description
- Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
- always
- false
- triggers
- task, tasks, create a task, track work, project, decompose, break down, plan the work, parallelize, work breakdown, goal loop, autonomous, organize work
Tasks & Projects
Bigger work is delivered by decomposing it into small, independently verifiable units, tracking those units as Tasks, and then executing them — some inline, some in parallel, some as an autonomous goal-driven loop.
Tasks — the unit of tracked work
A Task is a tracked, persisted unit of work with a title, description,
status, and dependency links. Tasks live in the Tasks entity, backed by the
native task provider and exposed over the /api/tasks CRUD:
GET /api/tasks/GET /api/tasks/{task_id}— list / fetch.POST /api/tasks— create a task.PATCH /api/tasks/{task_id}— update title, description, or status.DELETE /api/tasks/{task_id}— remove a task.GET /api/tasks/{task_id}/comments/POST— task discussion.GET /api/tasks/graph— the dependency graph (which tasks block which).
The dashboard Tasks page is the primary surface — create, organize, and watch status there. Use Tasks to make a decomposition visible and durable: one task per atomic unit, dependencies recorded, status updated as work progresses so nothing is dropped.
Project decomposition discipline
Before executing anything non-trivial, decompose:
- State the outcome in one sentence — what "done" looks like for the whole project.
- Break it into atomic units — each unit independently doable and independently verifiable. If a unit can't be checked on its own, it's still too big; split it. Record each as a Task.
- Map dependencies — which units block which. Independent units can run in parallel; dependent ones must be sequenced. Record the edges in the task graph so the order is explicit.
- Assign an execution mode per unit:
- trivial / fast / shared-context → do it inline.
- independent investigation or an isolated long task →
subagent_run(parallelize the independent ones). - open-ended "grind until the goal is met" → a goal loop (see below).
- Keep one coherent plan — track units and their state as Tasks so progress is visible. Integrate results back into the whole as units complete; don't just accumulate fragments.
Show full SKILL.md (277 more words)Show less
Goal loops — autonomous execution toward a goal
When the work is open-ended toward a definition of done — "grind on this
until it's met", a continuous-improvement target, a north-star objective — hand
it to a goal loop rather than driving it step-by-step yourself. A goal loop
classifies the target, decomposes it, then runs one self-directed cycle per turn
until a deterministic supervisor (or a separate judge) decides the goal is met,
at which point it self-retires. Goal loops are the unified autonomous goal
engine; manage them from the dashboard Goal Loops page. The per-cycle worker
protocol lives in the loop-worker skill.
Use a goal loop instead of trying to specify every step up front: you set the goal and the definition of done, the loop decides direction each cycle.
Parallel work with subagents
When several units are independent (no shared mutable state, no ordering
dependency), run them concurrently with subagent_run — e.g. investigate three
candidate root causes at once, or research several sub-questions in parallel —
then synthesize the returns. Keep each subagent's task self-contained with its
own clear deliverable so the results compose cleanly. (See delegation for the
spawn-vs-inline cost rule — don't spawn for trivial work.)
Discipline
- One unit = one verifiable step. Resist doing "the whole thing" in a single uncontrolled pass.
- Define done before starting — for the project and for each unit.
- Track it as a Task — a unit that isn't recorded gets dropped.
- Don't fan out work that shares mutable state — parallel workers stepping on the same files race. Parallelize only genuinely independent units.
- Re-plan when reality diverges — if a unit reveals the breakdown was wrong, update the plan and the tasks rather than forcing the old one.
© Sidiora-Labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in runtime/gideon/extensions/skills/bundled/task-and-project of Sidiora-Labs/centra-gideon-agent.
Open the folder on GitHubat commit 2176d5b
Compare with similar skills
Task And Project next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Task And Project this skillSidiora-Labs/centra-gideon-agent | 181 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from Sidiora-Labs/centra-gideon-agent
All 24 skills in this repoArtifacts
Sidiora-Labs/centra-gideon-agent
Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).
Best Of N
Sidiora-Labs/centra-gideon-agent
Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.
Document Authoring
Sidiora-Labs/centra-gideon-agent
Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.
Editorial Document
Sidiora-Labs/centra-gideon-agent
Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.
Gideon API
Sidiora-Labs/centra-gideon-agent
The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.
Infographic Syntax
Sidiora-Labs/centra-gideon-agent
Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.
Related
Categories
Questions about Task And Project
What does Task And Project do?
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one…. Task And Project is an agent skill from Sidiora-Labs/centra-gideon-agent. Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
When should I use Task And Project?
Task And Project fits situations like: tasks that involve Subagents.
How do I install Task And Project in Claude Code?
Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/task-and-project in Sidiora-Labs/centra-gideon-agent) into .claude/skills/task-and-project in your project. Claude Code loads it when a task matches its description.
How do I install Task And Project in Codex?
Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/task-and-project in Sidiora-Labs/centra-gideon-agent) into .agents/skills/task-and-project in your project. Codex loads it when a task matches its description.
Can I use Task And Project in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sidiora-Labs/centra-gideon-agent --skill task-and-project -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-and-project, .gemini/skills/task-and-project, .github/skills/task-and-project and .opencode/skills/task-and-project in your project.
What does Task And Project need to run?
SKILL.md names no scripts, command-line tools or credentials: Task And Project is instructions for the agent only.
Does Task And Project access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Task And Project safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Task And Project use?
Task And Project is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Task And Project use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Task And Project?
Skills that share tags, products or a category with Task And Project: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Task And Project?
Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 181 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.
Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.