harden-implementation-plan

A guided review process for testing and improving an implementation plan through questions, explanations, and repository inspection.

In plain words
What is it for?
Use it to understand, challenge, revise, and validate an implementation plan; it edits the plan but does not implement the planned product work.
Why use it?
It exposes unclear design decisions and checks whether the plan fits the existing system before implementation begins.

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/yourtechbud/coding-harness-config/harden-implementation-plan
Clone the repo
git clone --depth 1 https://github.com/YourTechBud/coding-harness-config
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 933 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 $0.00026 $0.00933
Opus 5 $0.00013 $0.00466
Sonnet 5 $0.00005 $0.00187
Haiku 4.5 $0.00003 $0.00093

Measured 3d ago against content hash a2c80fbff9b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harden-implementation-plan 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.

opencode/commands/harden-implementation-plan.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Socratic teaching to walk the user through the referenced implementation plan and revise it as their understanding and feedback develop.

The user should understand each load-bearing implementation neighborhood deeply enough to explain its purpose, predict relevant system behavior, form an implementation approach, compare that approach with the plan, and defend, reject, or improve the proposed design.

Read the complete plan and inspect the relevant repository implementation before beginning. Treat invocation as permission to edit the plan files when feedback settles. Do not implement the planned product work or edit files outside the plan.

Establish the journey

Identify the load-bearing neighborhoods in the architectural design and program design. A neighborhood is load-bearing when it is difficult to understand or when a different answer could materially change system behavior, responsibilities, interfaces, data flow, failure handling, phase structure, risk, or downstream work.

Open with a compact causal journey through the goal, the current system baseline, the proposed direction, and the load-bearing neighborhoods. Weave the neighborhoods and the consequences that make them important into the journey so the user can anticipate the route without receiving a mechanical agenda. Choose the teaching order that makes the system easiest to understand; it need not follow implementation order. Begin the first neighborhood as part of the opening.

Harden each neighborhood

Use Socratic teaching as an interplay between grounded explanation and consequential questions. Work in coherent conversational segments: provide enough related context for the user to reason, then invite them to explain, predict, propose, or judge where doing so deepens their understanding. Adapt the rhythm, depth, and number of questions to the neighborhood and the user's demonstrated knowledge.

Treat the user as a maintainer whose mental model of a changing codebase may be stale. Make the necessary context understandable from the conversation, use plain language, introduce important engineering terms before relying on them, and move past background the user already demonstrates.

Read the full file on GitHub · 46 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. 3d ago First seen · 46 lines · 26 tokens per session scan A a2c80fbff9b8

Subscribe to this mod's changes

harden-implementation-plan is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 933 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.