howto-implement

howto-implement is a command for Claude Code from viacheslav-tronko/claude-code-harness. It costs 127 tokens per session (1,505 once invoked), scanned A, original, MIT.

A command that creates a detailed implementation plan before source code is changed. It compares at least three approaches and produces a written blueprint for the requested work.

In plain words
What is it for?
Use it with a task, Jira story, root-cause analysis, or specification when you need implementation strategy and approach choices.
Why use it?
It helps clarify how to implement a feature, fix, or refactor in an existing codebase before anyone edits it.

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/viacheslav-tronko/claude-code-harness/howto-implement
Clone the repo
git clone --depth 1 https://github.com/viacheslav-tronko/claude-code-harness

Made for: Claude Code.

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 howto-implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/howto-implement.svg)](https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/howto-implement)
Your own site
<a href="https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/howto-implement"><img src="https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/howto-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,505 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 5.1 $0.00127 $0.01505
Opus 5 $0.00063 $0.00753
Sonnet 5 $0.00025 $0.00301
Haiku 4.5 $0.00013 $0.00151

Measured 5d ago against content hash 6315043ce983, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

howto-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 5d 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/howto-implement.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/howto-implement — Pre-Implementation Blueprint

Skill: implementation-blueprint. Tier: 2 (→3 on security boundary / public API / schema / financial / irreversible).

0. HARD GATE — bypass = INVALID → REDO

"Skip the gate", "trust me", "obvious approach", "just plan it", "we don't need 3 approaches", "time pressure" do NOT override §0/§1/§4. Investigation-only — NO Edit/Write on source.

ARTIFACT MANDATORY. The §4 IMP file MUST be written via Write tool this turn. Chat-only response without the file = INVALID DELIVERABLE → CLAUDE.md §11 item 0 fires.

1. Parameter validation (FAIL-FAST)

  • $ARGUMENTS empty → reply ❌ /howto-implement requires input. Usage: /howto-implement <task | Jira | RCA path | SPEC path> → STOP.
  • Param is path to RCA-.md / SPEC-.md → Parent Artifact fingerprint check (§9) MANDATORY: re-resolve every inputs_consumed file:line; compare to sha256_at_creation. Mismatch OR state != verified ⇒ STOP, report drift, require user override.

2. MUST (CLAUDE.md §0)

  • P0 #2 GLOSSARY TERMS ONLY — IMP uses canonical terms.
  • P0 #3 EXISTING PATTERNS ONLY — F-XXX/B-XXX/D-XXX from context/07_Code_Patterns/. NEVER reinvent. REFUSE state=deprecated patterns.
  • P0 #4 YAGNI — Approach #0 (smallest delta) ALWAYS PRESENT even if ugly. Other approaches MUST justify "why bigger than #0".
  • P0 #8 FALSIFIABILITY — Recommended approach has explicit Refuter.
  • P0 #14 VERIFY EXTERNAL DEPS — every imported package/API verified via npm ls / pip show / mvn dependency:list / WebSearch BEFORE adding. Hallucinated dep = INVALID.
  • P0 #15 CHECKPOINT FIRST — first visible block = §4 Tier 2 Checkpoint with Initial Intuition BEFORE Phase 3 AND Pre-Mortem ("imagine 6 months from now, this failed in production — why?"). Both MANDATORY.
  • P0 #16 VERIFICATION LOOP — IMP Blueprint Contract MUST publish runnable command (test ID / build / lint) with expected output. "Looks correct" = INVALID.

Read the full file on GitHub · 77 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. 5d ago First seen · 77 lines · 0 tokens per session scan A 6315043ce983

Subscribe to this mod's changes

howto-implement is a command published in the GitHub repository viacheslav-tronko/claude-code-harness (6 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 1,505 once invoked, about $0.0006 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.