implement

A command that runs a previously written coding plan step by step through a coordinated implementation and review process.

In plain words
What is it for?
Use it to apply a plan file, validate that the plan is recent and complete, retry failed steps, and record the results.
Why use it?
It prevents the agent from losing the plan’s structure and requires each step to meet its stated checks before continuing.

Command

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/valsecchi75/project-scaffolder/implement
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 355 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 $0.00027 $0.00355
Opus 5 $0.00014 $0.00178
Sonnet 5 $0.00005 $0.00071
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash 5617f0bcca96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/implement.md · 46 lines

What it actually says

/implement

Execute an existing plan. Wrapper around /task that uses a plan file as structured input.

Usage

/implement <plan-file-path>
/implement @latest

Examples

/implement docs/superpowers/plans/2026-04-17-pull-to-refresh.md
/implement @latest

Steps

  1. Resolve plan path:
    • If @latest → pick the most recent file in docs/superpowers/plans/
    • Otherwise → read the provided path
  2. Validate plan structure:
    • Has Goal, Steps, VERIFY criteria on every step
    • Plan file is less than 7 days old (otherwise context may be stale)
  3. Pass the full plan to Cortex as primary context.
  4. Cortex executes step-by-step:
    • Specialist implements step N
    • QA Agent verifies step N against its VERIFY criterion
    • If FAIL → return to specialist for that step only (max 2 iterations per step)
    • If PASS → proceed to step N+1
  5. Log each step outcome to logs/pipeline/YYYY-MM-DD.md.

Rules

  • Refuse plans without VERIFY criteria on every step.
  • Refuse plans older than 7 days — ask the user to regenerate.
  • Max 2 iterations per step (stricter than default /task because the plan should have been pre-thought).
  • If a step fails twice: stop, report to user, document in wiki/debugging/failed-experiments.md.
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 · 46 lines · 27 tokens per session scan A 5617f0bcca96

Subscribe to this mod's changes

implement is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 355 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.