ai-engineering: Skill for Claude Code

.agents/skills/ai-plan/SKILL.md

ai-plan is a skill for Claude Code from arcasilesgroup/ai-engineering. It costs 121 tokens per session (859 once invoked), scanned A, original, Apache-2.0.

A planning workflow that turns an approved specification into a numbered task list. Each task names one file, a command that should fail before the change, a rollback, and a testable completion condition.

In plain words
What is it for?
Breaking specifications into coding tasks, defining checks and rollback steps, and including deployment and monitoring work when a change will be publicly reachable.
Why use it?
It makes implementation work small, reversible, and measurable instead of leaving progress to personal judgement.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is arcasilesgroup/ai-engineering's own configuration. It tells Claude Code how to work on ai-engineering itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arcasilesgroup/ai-engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arcasilesgroup/ai-engineering/main/.agents/skills/ai-plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arcasilesgroup/ai-engineering

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 ai-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-plan.svg)](https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-plan)
Your own site
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-plan"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00121 $0.00859
Opus 5 $0.00060 $0.00430
Sonnet 5 $0.00024 $0.00172
Haiku 4.5 $0.00012 $0.00086

Measured 7d ago against content hash 4f330b4dab58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-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 7d 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/ai-plan/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn the spec into tasks

What it produces

specs/NNN-slug/plan.md, beside the spec it implements.

Steps

  1. Read the spec, and only the specs it names — the one it supersedes, the ones it depends on. Nothing else. A hundred specs cost the index plus the ones you were told about.
  2. Write tasks small enough that each one is a commit, each one numbered and each one opening with an empty box: 1. [ ] **Title** —. For every task, four things: file (the one it touches), check (the command that fails today and passes after), rollback (how to undo it), done when (in one sentence, testable). Never write [x]. The box is filled by ai-eng spec show <id> --task <n> --tick, which runs the check and seals what it measured; an empty box means no command has run over these bytes yet, which is not the same as "not done".
  3. A check is a command, never a judgement. "Looks right" is not a check. If a task's check reads "the agent decides X", say in one line why a script cannot do it — and if you cannot say why, write the script instead. That is rule 12, and it applies here first because here is where the cost is decided.
  4. If the spec adds anything that gets a URL, two tasks are mandatory and named:
    • a CI/CD task: build, lint, test and security analysis on every push, deploy from the default branch, zero manual steps;
    • an observability task covering the eight signals the spec lists, each passing with a command. Without them the plan is not finished, whatever else is in it.
  5. Order the tasks so that the first failing check appears as early as possible. A plan whose first six tasks cannot fail is a plan that finds out too late.
  6. Say what you are not doing, and why. The deliberate omissions are the part reviewers most often need and least often get.

Done when

  • Every task has a file, a check, a rollback and a "done when".
  • The deployable tasks exist if the spec is deployable, and are absent if it is not.
  • The person has approved it, recorded as an ADR at the spec and plan digests. That record is the gate: no code before it.
  • The reviewer got ai-eng report view --spec <NNN>'s file:// link beside the Markdown; the ADR at the two digests stays the gate, and the page is how it is read.

Read the full file on GitHub · 62 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 62 lines · 121 tokens per session scan A 4f330b4dab58

Subscribe to this mod's changes

ai-plan is a skill published in the GitHub repository arcasilesgroup/ai-engineering (54 stars, last pushed 5d ago), licensed Apache-2.0. It adds 121 tokens to every session and 859 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 2026-08-30.