Agency Scaffold Generator Agent Skill

Generate scaffolds that gradually increase student choice, voice, and ownership within a learning task.

Context cost
5.7k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 22.6 kBtext throughout, nothing executable
Licence
Source-availablethe author’s own terms
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Generate scaffolds that gradually increase student choice, voice, and ownership within a learning task. Use when students depend heavily on teacher direction and need to develop autonomy.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

agencyautonomychoicedocumentationgradual-releaseself-regulationstudent-voice

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md22.6 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: agency-scaffold-generator disable-model-invocation: false user-invocable: true effort: medium # EXISTING FIELDS skill_id: "wellbeing-motivation-agency/agency-scaffold-generator" skill_name: "Agency Scaffold Generator" domain: "wellbeing-motivation-agency" version: "1.0" evidence_strength: "moderate" evidence_sources: - "Zimmerman (2002) — Becoming a self-regulated learner: an overview" - "Deci & Ryan (2000) — The 'what' and 'why' of goal pursuits: human needs and self-determination" - "Reeve & Tseng (2011) — Agency as a fourth aspect of student engagement" - "Manyukhina & Wyse (2019) — Learner agency and the curriculum: a critical realist perspective" - "Mercer (2011) — Understanding learner agency as a complex dynamic system" input_schema: required: - field: "current_task" type: "string" - field: "student_level" type: "string" - field: "current_agency_level" type: "string" optional: - field: "subject_area" type: "string" - field: "learning_objective" type: "string" - field: "student_profiles" type: "array" - field: "agency_dimension" type: "string" output_schema: type: "object" fields: - field: "agency_scaffold" type: "object" - field: "choice_architecture" type: "object" - field: "safety_nets" type: "array" - field: "teacher_role_shifts" type: "array" chains_well_with: - "motivation-diagnostic-task-redesign" - "self-efficacy-builder-sequence" - "self-regulated-learning-strategy-selector" - "metacognitive-prompt-generator" teacher_time: "3 minutes" tags: ["agency", "student-voice", "choice", "autonomy", "self-regulation", "gradual-release"] ---
70# Agency Scaffold Generator
71
72## What This Skill Does
73
74Generates a structured scaffold for progressively releasing decision-making to students — moving from teacher-directed to student-directed learning in specific, manageable steps across five dimensions of agency: choice of topic, choice of process, choice of product, choice of criteria, and choice of timeline. The critical principle is that agency is not binary (teacher controls vs. student controls) but a continuum that must be scaffolded — giving full agency to students who have never had it is as counterproductive as never giving agency at all. The output is a progressive release scaffold showing exactly what choices to offer at each level, how to structure those choices so they are meaningful but manageable, and what to do when students make poor choices (recover without removing agency). AI is specifically valuable here because scaffolding agency requires balancing two competing demands: enough structure that students don't flounder, and enough freedom that the choices are genuine — and this balance point is different for every class, every subject, and every task.
75
76## Evidence Foundation
77
78Zimmerman (2002) established that self-regulation — the capacity to direct one's own learning — is developed through explicit teaching and gradual release. Students don't become self-directed by being given freedom; they become self-directed by being taught the skills of self-direction and practising them in increasingly open contexts. Deci & Ryan (2000) demonstrated that autonomy — the sense that one's actions are self-endorsed — is a basic psychological need that, when satisfied, enhances intrinsic motivation and deeper learning. However, autonomy requires SUPPORT, not just FREEDOM. Autonomy support means providing rationale, acknowledging the student's perspective, and offering meaningful choice — not removing all structure. Reeve & Tseng (2011) identified agency as a fourth dimension of student engagement (alongside behavioural, emotional, and cognitive engagement), showing that students who exercise agency — who contribute to the learning process rather than passively receiving it — show deeper engagement and better outcomes. Manyukhina & Wyse (2019) argued that learner agency must be understood within curriculum structures — agency doesn't mean "students choose everything" but that students have genuine decision-making power within a purposeful learning framework. Mercer (2011) showed that agency is not a fixed trait but a dynamic system influenced by context, confidence, prior experience, and the specific demands of the task.
79
80## Input Schema
81
82The teacher must provide:
83- **Current task:** The activity where agency will be scaffolded. *e.g. "Year 9 history essay on the causes of WW1" / "Year 7 science investigation into plant growth" / "Year 10 English literature coursework"*
84- **Student level:** Year group. *e.g. "Year 9"*
85- **Current agency level:** Where students are now. *e.g. "Very dependent — they wait for the teacher to tell them exactly what to do at every step" / "Some independence — they can work through a task but don't make choices about how to approach it" / "Moderate — they can choose between options but struggle with open-ended tasks"*
86
87Optional (injected by context engine if available):
88- **Subject area:** The curriculum subject
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md3,355 words
Files1
LicenceSource-available
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈740
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,910
on trigger
The instruction body, read only when the skill fires.
2.8%
of a 200k window
Ten skills this size would take about 28% of the window before you open a file.
050k100k150k200k context window

5.7k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 22.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md22.6 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The Source-available licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Agency Scaffold Generator · 5.7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/agency-scaffold-generator/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/agency-scaffold-generator" ] && { [ ! -e .claude/skills/agency-scaffold-generator ] || { mv .claude/skills/agency-scaffold-generator "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/agency-scaffold-generator" .claude/skills/ && echo "Installed .claude/skills/agency-scaffold-generator"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/agency-scaffold-generator

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/agency-scaffold-generator/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/agency-scaffold-generator/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/agency-scaffold-generator" ] && { [ ! -e ~/.claude/skills/agency-scaffold-generator ] || { mv ~/.claude/skills/agency-scaffold-generator "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/agency-scaffold-generator" ~/.claude/skills/ && echo "Installed ~/.claude/skills/agency-scaffold-generator" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/agency-scaffold-generator/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version1.0
Publishedno release date on file
PriceFree
Referencegarethmanning/agency-scaffold-generator

Versions

v1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill