speckit.implement

An implementation command that reads a project’s task plan and carries out its development tasks, with options for previews, phases, individual tasks, confirmations, and failure handling.

In plain words
What is it for?
Use it to execute all planned tasks, run one phase or task, preview changes with a dry run, or stop when a task fails.
Why use it?
It reduces the manual work of following a multi-step implementation plan and provides controls for how tasks are run.

Command for Claude Code

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.

agentmods
npx agentmods add commands/pilotspace/pilot-space/speckit.implement
Clone the repo
git clone --depth 1 https://github.com/pilotspace/pilot-space

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.02173
Opus 5 $0.00007 $0.01086
Sonnet 5 $0.00003 $0.00435
Haiku 4.5 $0.00001 $0.00217

Measured 2d ago against content hash a25f100aa0db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/speckit.implement.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty). Load @docs/dev-pattern/README.md for project rules.

Flags

Flag Description Default
--interactive Prompt for confirmations (checklist, failures) false
--stop-on-failure Halt on first task failure false
--skip-checklists Skip checklist validation entirely false
--phase {N} Execute specific phase only all
--task T{ID} Execute single task all
--dry-run Preview execution plan without changes false

Workflow

Phase 1: Prerequisites

Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks from repo root. Parse JSON for FEATURE_DIR and AVAILABLE_DOCS (use absolute paths).

For single quotes in args like "I'm Groot", use escape syntax: 'I'\''m Groot' or double-quote.

Phase 2: Checklist Validation

Skip this phase if --skip-checklists flag is set or FEATURE_DIR/checklists/ does not exist.

Scan checklist files:

  • Count total items: Lines matching - [ ] or - [X] or - [x]
  • Count completed: Lines matching - [X] or - [x]
  • Count incomplete: Lines matching - [ ]

Display status table:

| Checklist   | Total | Completed | Incomplete | Status   |
|-------------|-------|-----------|------------|----------|
| ux.md       | 12    | 12        | 0          | PASS     |
| test.md     | 8     | 5         | 3          | FAIL     |
| security.md | 6     | 6         | 0          | PASS     |

Behavior:

Condition Default (automatic) With --interactive
All checklists complete Proceed to Phase 3 Proceed to Phase 3
Some checklists incomplete Log warning, proceed Ask user confirmation

Warning format (automatic mode):

Proceeding with incomplete checklists (use --interactive to prompt)

Phase 3: Load Context

Read the full file on GitHub · 271 lines

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.

  1. 2d ago First seen · 271 lines · 14 tokens per session scan A a25f100aa0db

Subscribe to this mod's changes

speckit.implement is a command published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 2,173 once invoked, about $0.0001 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 2026-08-31.