implement

A coding workflow for implementing one ready item from a project's specification work list. It requires reading the repository guidance and full specification before coding, then validating the result.

In plain words
What is it for?
Use it to select an unblocked ready specification, implement it, run the project's tests and lint checks, and record the work according to the repository process.
Why use it?
It keeps implementation tied to the written specification instead of guesses based on existing code. It also prevents taking multiple work items at once and catches problems through tests and linting.

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/justifi-tech/web-component-library/implement
Clone the repo
git clone --depth 1 https://github.com/justifi-tech/web-component-library

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 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 $0.00000 $0.00515
Opus 5 $0.00000 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured yesterday against content hash 782f28772d08, 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 yesterday.

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/specd/implement.md · 39 lines

What it actually says

Study AGENTS.md for guidelines. Study specs/README.md to understand the spec system and find specs with status "Ready". Read specd_work_list.md in full — it contains all remaining work items.

Your task is to implement ONE work item from specd_work_list.md, then validate it works.

IMPORTANT:

  • Read AGENTS.md first — specs are the source of truth, not existing code
  • Pick an unblocked item from specd_work_list.md — an item is unblocked if and only if its line does NOT contain the string (blocked:. Items without that string are ready to implement regardless of what version or section they're in.
  • Read the full spec for context before implementing — the work item is a summary, the spec has the detail
  • Only implement specs with status "Ready"
  • NEVER change spec status in specs/README.md or individual spec files
  • If code contradicts the spec, fix the code first (see AGENTS.md)
  • Commit your changes
  • Do NOT use TodoWrite — just do the work
  • Do NOT do multiple things — ONE thing per iteration

After implementing, VALIDATE before recording completion:

  • Run pnpm test — unit tests must pass
  • Run pnpm lint — no warnings allowed (--max-warnings 0)
  • If changes affect component behavior visible in the browser, run pnpm test:e2e
  • Only fix linting errors in files you modified

After validation, update tracking files:

  1. Add a line at the TOP of specd_history.md (below the header comment) in the format: - **spec-name v0.1 (YYYY-MM-DD):** work item text (use the work item text from specd_work_list.md as the description)
  2. Remove the completed item from specd_work_list.md.
  3. Check specd_work_list.md for items with (blocked: ...) annotations that reference the work you just completed. If the blocker is resolved, remove the (blocked: ...) annotation. Output TASK_COMPLETE: true when done.

Before declaring LOOP_COMPLETE, re-read specd_work_list.md and list every remaining item. For each item, check: does the line contain (blocked:? If ANY item does NOT contain (blocked:, you are NOT done — pick one and implement it.

Output LOOP_COMPLETE: true only if every remaining item in specd_work_list.md contains (blocked: on its line, or the file is empty.

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. yesterday First seen · 39 lines · 0 tokens per session scan A 782f28772d08

Subscribe to this mod's changes

implement is a command published in the GitHub repository justifi-tech/web-component-library (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 515 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 2026-08-31.