spec-implement

spec-implement is a command for coding agents from techtalk/ai-readiness-assessment. It costs 41 tokens per session (344 once invoked), scanned A, original, Apache-2.0.

A command that turns a written feature specification into a reviewed implementation plan and then guides test-first development. TDD, or test-driven development, means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it with a specification to extract requirements, write a plan, pause for adversarial review, create the failing test, implement the smallest change, run tests and linting, and open a linked pull request.
Why use it?
It creates a documented plan and requires human review of risks and objections before implementation begins.

Command

Part of the ai-readiness-assessment plugin — 3 skills, 3 commands, 1 plugin shipped together

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/techtalk/ai-readiness-assessment/spec-implement
Clone the repo
git clone --depth 1 https://github.com/techtalk/ai-readiness-assessment

Or install ai-readiness-assessment, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 plugin.

Wrote 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.

agentmods badge for spec-implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/techtalk/ai-readiness-assessment/spec-implement.svg)](https://agentmods.dev/commands/techtalk/ai-readiness-assessment/spec-implement)
Your own site
<a href="https://agentmods.dev/commands/techtalk/ai-readiness-assessment/spec-implement"><img src="https://agentmods.dev/badge/commands/techtalk/ai-readiness-assessment/spec-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00041 $0.00344
Opus 5 $0.00020 $0.00172
Sonnet 5 $0.00008 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured 3d ago against content hash e6b87e3b5865, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-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 3d 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.

tests/fixtures/level-4-specs/commands/spec-implement.md · 37 lines

What it actually says

/spec-implement

Project-local command. Orchestrates the spec-first workflow.

Usage

/spec-implement specs/NNNN-<slug>.md

Process

  1. Read the spec. Identify the "what", the "why", the acceptance criteria, and the explicit "out of scope" boundaries.
  2. Draft the plan. Write a plan under specs/plans/NNNN-<slug>-plan.md covering: approach, steps, risks, verification.
  3. Pause for adversarial review. Tell the human: "Plan is at specs/plans/NNNN-<slug>-plan.md. Walk through the adversarial review and record dispositions under docs/objections/NNNN-<slug>.md. Return here when all dispositions are resolved."
  4. Wait for human confirmation that objections are resolved.
  5. Write the failing test described in the acceptance criteria.
  6. Confirm the test is red for the right reason.
  7. Write the minimal production code to make the test pass.
  8. Run the full test suite and the linter. Confirm green.
  9. Open the PR, referencing the spec by path in the PR body.

Do not proceed past step 3 until the human confirms the objection dispositions are resolved.

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. 3d ago First seen · 37 lines · 41 tokens per session scan A e6b87e3b5865

Subscribe to this mod's changes

spec-implement is a command published in the GitHub repository techtalk/ai-readiness-assessment (9 stars, last pushed 16d ago), licensed Apache-2.0. It adds 41 tokens to every session and 344 once invoked, about $0.0002 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.