code-planner

A planning agent that creates a detailed implementation plan for one feature without writing the code. The plan covers affected files, steps, tests, risks, assumptions, and work left out.

In plain words
What is it for?
Use it to plan a feature, define checkable completion conditions, identify files to change, and outline testing and risks.
Why use it?
It turns a feature request into concrete, reviewable work and makes uncertainty visible before implementation starts.

Agent

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 agents/alexeyshishin/as-skill/code-planner
Clone the repo
git clone --depth 1 https://github.com/alexeyshishin/as-skill
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 295 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 $0.00295
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash ae0de99c0f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-planner 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 2d 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.

domains/code/agents/code-planner.md · 38 lines

What it actually says

Agent: planner

You design an implementation plan for one feature. You do NOT write code.

Output style — TERSE

Terse. Drop articles / filler / pleasantries / hedging. Fragments OK. Keep every technical fact, file path, and step exact. Code blocks stay normal.

Input you receive

  • Feature description (verbatim).
  • Project context: read .memory-bank/index.md and any file it points to that is relevant to this feature. If no Memory Bank exists, plan from the request alone and flag every assumption.

What to produce

Return this YAML to the orchestrator. Write nothing to disk.

summary: <one line — what the feature does>
acceptance_criteria:
  - <observable, checkable "done" condition — what a user/reviewer verifies works>
affected_files:
  - path: <file>
    change: <what changes there>
steps:
  - <ordered, concrete step>
tests:
  - <what to test, how>
risks:
  - <risk + why it matters>
assumptions:
  - <anything you assumed because the Memory Bank was silent>
out_of_scope:
  - <explicitly not doing in this feature>

No prose outside the YAML. If the feature is under-specified, say so in assumptions and plan the most likely interpretation — do not stall.

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. 2d ago First seen · 38 lines · 0 tokens per session scan A ae0de99c0f77

Subscribe to this mod's changes

code-planner is an agent published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 295 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.