github/spec-kit-copilot is a repository of GitHub Copilot integrations for Spec Kit, a toolkit for developing software through a structured specification-first workflow. It provides Copilot-specific commands, skills, canvases, and related workflow components for users of the Copilot CLI, Copilot App, and VS Code.
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.
git clone --depth 1 https://github.com/github/spec-kit-copilotWrote 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.
[](https://agentmods.dev/commands/github/spec-kit-copilot/load-page)<a href="https://agentmods.dev/commands/github/spec-kit-copilot/load-page"><img src="https://agentmods.dev/badge/commands/github/spec-kit-copilot/load-page/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.
<a href="https://agentmods.dev/commands/github/spec-kit-copilot/load-page"><img src="https://agentmods.dev/badge/commands/github/spec-kit-copilot/load-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.00708 |
| Opus 5.5 | $0.00005 | $0.00283 |
| Sonnet 5.5 | $0.00002 | $0.00142 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
load-page 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
$ARGUMENTS supplies the Wizard handoffId and, for an explicit reload, the
requestId. Preserve these values in the tool call. Work in this session's
project, not the Wizard's checkout. If the handoff ID is missing, ask for it;
do not guess or select another session's handoff.
Pages
Load these default pages:
canvas-settings-setupcanvas-settings-artifactscanvas-settings-appearancecanvas-settings-results
Presets may add pages in sections titled Additional Designer pages anywhere in this command, including after the Steps. These additions extend the default set; they do not run a second load operation.
Steps
-
Read this entire composed command first. Collect the defaults and every name in every Additional Designer pages section, removing duplicates. Page names must start with a lowercase letter and contain only lowercase letters, digits and hyphens (at most 80 characters).
-
Follow the
speckit-presetskill to runspecify preset resolve <name>for each name from the project root. Resolve all pages before submitting any. Use Specify CLI >=1.0.7. Its human-readable output looks like:canvas-settings-setup: C:\project\.specify\extensions\extension-canvas-design\pages\setup.json (top layer from: extension:extension-canvas-design v0.1.0)Ignore leading indentation and record the complete path following the exact
<name>:prefix. Preserve spaces and drive-letter colons; do not split on every colon. If output wraps, rerun with a sufficiently wideCOLUMNSenvironment setting rather than guessing a truncated path. -
Inspect the output AND exit status.
not foundcan return exit code 0. Stop on missing/ambiguous results, command errors, or a composition warning for a page. Never choose a file by scanning.specify, reconstruct precedence, or substitute an extension default. Appended instructions in this command are allowed; composing multiple complete JSON documents for a page is not. -
Call the custom
speckit_designer_load_pagestool exactly once withhandoffId, the suppliedrequestIdif present, andpages: [{"name": "<template-name>", "path": "<resolved-path>"}, ...]. Submit the entire collected set, not individual pages. This tool is provided by the installed Canvas Designer Copilot extension, not by Specify. -
Report the tool's result. On success, the validated model is ready for Designer. The launching agent may now open
speckit-canvas-designerusing the samehandoffId; a reload updates already-open panels automatically. Do not claim that opening or loading succeeded before the tool succeeds.
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.
- 14d ago Changed 618dcd81766c
- 15d ago First seen · 62 lines · 12 tokens per session scan A b64f6c5ee6d2
load-page is a command published in the GitHub repository github/spec-kit-copilot (17 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 708 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-01.
Other commands, from other repositories
sdd-reverse-specify
Reverse specification — reconstruct existing behaviour from code, tests or a plan into a human-validated Baseline spec. Resumable.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-systemdesign
Command description: Create or refine the canonical software architecture document. Argument hint: [project description, docs, constraints, or architecture inputs] Command category: project-bootstrap Prerequisites: none.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode), issue tracker.
apex-git-commit
Stage everything except agent-output/, infra/, and .github/skills/sensei/ (unless on feat/skills-sensei), auto-generate a conventional commit, push, then prompt to open or update a PR. CLI-only (git + gh).
extract-foundations-from-screens
Extract canonical foundations docs (color, typography, spacing, radii) from a batch of existing SCREENSPECs. Re-runs only add new tokens and route conflicts to a Review queue. Use when SCREENSPECs already document raw values and need converging into role tokens. Do not use when foundations are already curated and…