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.
npx agentmods add commands/github/spec-kit-copilot/speckit.implementgit clone --depth 1 https://github.com/github/spec-kit-copilotWhat 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 | $0.00000 | $0.00414 |
| Opus 5 | $0.00000 | $0.00207 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
speckit.implement 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 2d 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.
What it actually says
Sub-Agent Delegation
When executing this command, delegate independent work to parallel sub-agents to reduce total execution time.
How to dispatch sub-agents in Copilot:
- VS Code: Use the
runSubagenttool to spawn each sub-agent in an isolated context. - CLI: Delegate to a sub-agent process — Copilot CLI automatically manages subsidiary sub-agent execution. You can also target custom agents defined in
.github/agents/or~/.copilot/agents/.
Parallel Task Execution
When processing tasks within a phase, identify all tasks marked with [P] (parallel-safe). Dispatch each parallel-safe task as a separate sub-agent:
- For each
[P]task in the current phase: → Sub-agent: "Implement task {TaskID}: {description}. Context: {relevant plan/spec excerpts}. File path: {target file}. Return: confirmation of completion, files created/modified, and any issues encountered."
Rules for sub-agent dispatch:
- Only dispatch tasks within the same phase — never cross phase boundaries
- Sequential tasks (without
[P]) must run in the main agent, in order - If a parallel task depends on a sequential task in the same phase, wait for the sequential task first
- After all sub-agents for a phase complete, verify results in the main agent before moving to the next phase
- Mark each completed task as
[X]in tasks.md after verifying the sub-agent's output
Context Loading in Parallel
When loading implementation context (step 3), dispatch parallel reads:
- Sub-agent: Load plan context — "Read plan.md and extract tech stack, architecture decisions, and file structure. Return a structured summary."
- Sub-agent: Load supporting docs — "Read data-model.md, contracts/, research.md, and quickstart.md (whichever exist). Return a consolidated context summary."
Use the consolidated results to inform implementation.
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.
- 2d ago First seen · 33 lines · 0 tokens per session scan A e53e08198db7
speckit.implement is a command published in the GitHub repository github/spec-kit-copilot (11 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 414 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 2026-08-30.
Other commands, from other repositories
spec-kitty.analyze
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
sdd-plan
Turn a spec into a persisted baby-step plan file — research, resume, impact analysis.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
sdd-clarify
Adversarial pass over a finished spec — contradictions, ambiguity, untestable criteria, implementation posing as intent, missing failure modes.
plan
Run /plan — see .claude/commands/plan.md for the authoritative spec.
epic-plan
Run /epic-plan — see .claude/commands/epic-plan.md for the authoritative spec.