agent-planning

A planning guide for turning a written requirement into a file-by-file implementation plan for a toolkit repository.

In plain words
What is it for?
Use it to map affected files, split independent concerns, define small tasks, and choose checks such as shell syntax tests or spelling checks.
Why use it?
It clarifies the work before files are changed and helps keep related documentation, scripts, and overlays consistent.

Skill for Claude CodeCodex

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/sflandergan/agentic-coding/agent-planning
Any agent
npx skills add sflandergan/agentic-coding --skill agent-planning
Clone the repo
git clone --depth 1 https://github.com/sflandergan/agentic-coding

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 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 $0.00025 $0.00731
Opus 5 $0.00013 $0.00365
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured yesterday against content hash d208d1e04820, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 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.

.agents/skills/agent-planning/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Planning — Self-Maintenance

Write lightweight implementation plans for this toolkit repo. There is no application code — the maintenance surface is markdown templates and bash scripts.

Announce at start: "I'm using the agent-planning skill to create the implementation plan."

Save plans to: plans/YYYY-MM-DD-<feature-name>/plan.md, next to the spec.

Scope Check

If the spec covers multiple independent concerns, suggest splitting into separate plans.

File Mapping

Before defining tasks, map out which files will be created or modified. For each file:

  • What it is responsible for
  • Whether a stacks/* overlay also needs updating (core+stacks dual-maintenance)
  • Whether README.md, this repo's skills-lock.json, core/skills-lock.json, or the dot-mapping table need updates for their distinct scopes

Task Granularity

Each task is one focused commit. Steps within a task are small concrete actions:

  • "Write the file" — step
  • "Verify syntax" — step
  • "Commit" — step

Verification should match the changed files: shellcheck and bash -n for bash scripts, smoke runs for script behavior changes, codespell for prose-heavy changes, and consistency checks for README, lockfiles, symlinks, and dot-mapping.

Spellcheck Planning

When a task creates or modifies markdown templates, agent files, skill files, README content, or user-facing script text, include a codespell verification step for the changed files. Keep it scoped to the files touched by the task unless the plan intentionally adds or updates repo-wide spelling policy.

Plan Document Header

# [Feature Name] Implementation Plan

> **For implementation agents:** Execute this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

**Goal:** [One sentence]

**Configuration shape:** [2-3 sentences]

**Configuration surface:** [Key files, tools, and validation commands]

Task Structure

### Task N: [Component Name]

**Files:**
- Create: `exact/path/to/file`
- Modify: `exact/path/to/existing`

- [ ] **Step 1: [Action]**

[Content — exact paths, complete file content or commands]

- [ ] **Step 2: Verify**

Run: `shellcheck scripts/foo.sh`
Run: `codespell exact/path/to/file.md`
Expected: no errors

- [ ] **Step 3: Commit**

```bash
git add path/to/file
git commit -m "chore: description"

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 25 tokens per session scan A d208d1e04820

Subscribe to this mod's changes

agent-planning is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 731 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens