engineering-planning

engineering-planning is a skill for Claude Code, Codex from fqmyysjjd/agent-feed. It costs 38 tokens per session (664 once invoked), scanned A, original, MIT.

A planning checklist for software changes, covering where new work belongs, what existing code can be reused, and how it should fit the project.

In plain words
What is it for?
It is used before writing code, tests, files, refactors, or dependencies to inspect the project rules and identify the correct module or layer to change.
Why use it?
It helps prevent misplaced files, duplicated logic, and implementation decisions made without understanding the project's structure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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 skills/fqmyysjjd/agent-feed/engineering-planning
Any agent
npx skills add fqmyysjjd/agent-feed --skill engineering-planning
Clone the repo
git clone --depth 1 https://github.com/fqmyysjjd/agent-feed

Made for: Claude Code, Codex.

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 engineering-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/engineering-planning.svg)](https://agentmods.dev/skills/fqmyysjjd/agent-feed/engineering-planning)
Your own site
<a href="https://agentmods.dev/skills/fqmyysjjd/agent-feed/engineering-planning"><img src="https://agentmods.dev/badge/skills/fqmyysjjd/agent-feed/engineering-planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 664 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 $0.00038 $0.00664
Opus 5 $0.00019 $0.00332
Sonnet 5 $0.00008 $0.00133
Haiku 4.5 $0.00004 $0.00066

Measured 5d ago against content hash 657a3952698b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

engineering-planning 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.

.agents/skills/engineering-planning/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Planning

Required Use

Use this skill before any task that writes code, creates files, changes tests, moves project structure, introduces dependencies, or changes implementation behavior.

This skill exists to prevent "just add a file" work. The output must explain where the change belongs, what can be reused, and how the implementation will remain maintainable.

Required Reading

  1. .agents/rules/outcome-boundary.md
  2. .agents/project/README.md
  3. .agents/project/project-structure.md
  4. .agents/project/architecture-boundaries.md
  5. .agents/domain/contracts.md
  6. The nearest existing module, helper, adapter, command, test, or document that already owns related behavior.

Workflow

Before editing:

  1. Recover the current Task Brief and stop condition.
  2. Identify the owning layer: rule, skill, project constraint, domain knowledge, source module, script, adapter, test, or documentation.
  3. Search existing code, tests, helpers, templates, scripts, and docs for reusable behavior before creating anything new.
  4. Decide whether the change should extend an existing owner, create a small new owner, or avoid code changes entirely.
  5. Check whether the placement preserves project structure, source-of-truth ownership, public contracts, configuration boundaries, and generated-template boundaries.
  6. Choose the smallest write set that can satisfy the result without scattering related behavior.
  7. Decide the verification evidence before editing.

Engineering Planning Card

For non-trivial implementation or fix work, keep this compact card in working notes or the user-facing plan:

| Item | Decision |
| --- | --- |
| Owner | Existing module/file/layer that should own the change |
| Reuse | Existing code, helper, pattern, test, or doc to reuse |
| Placement | Where the change belongs and why |
| Write set | Files/directories expected to change |
| Boundary | Public contract, config, template, adapter, security, or project boundary to preserve |
| Verification | Tests/checks that prove the result |

Read the full file on GitHub · 71 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 · 71 lines · 38 tokens per session scan A 657a3952698b

Subscribe to this mod's changes

engineering-planning is a skill published in the GitHub repository fqmyysjjd/agent-feed (4 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 664 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.