skill-files

A set of development rules for SKILL.md files, which are instruction files that teach an agent how to perform a task.

In plain words
What is it for?
Writing or reviewing skill files, organizing supplementary references, and checking that required announcements and session-state instructions are present.
Why use it?
It keeps these instruction files within a size limit and places templates, diagrams, and large reference material in separate files.

Cursor rule for Claude Code

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 rules/aimeerrhythm/enterprise-change-workflow/skill-files
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow

Made for: Claude Code.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 321 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 $0.00321
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured yesterday against content hash 6cd0ad2ee27e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-files 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.

.claude/rules/skill-files.mdc · 39 lines

What it actually says

SKILL.md Conventions

Size Budget

SKILL.md MUST stay under 400 lines. If exceeding, extract content into supplementary files.

REFERENCE/TEMPLATE Extraction

SKILL.md only contains execution logic. Extract the following into same-directory supplementary files:

  • Output templates → *-template.md
  • Lookup tables / DOT diagrams → *-reference.md / *-diagram.md
  • Large inline prompts → dedicated files

Supplementary files are loaded on-demand via Read references, not embedded in SKILL.md.

Mode-Switch + Announce-at-Start (ALL skills)

Every SKILL.md MUST declare near the top (after Overview):

  1. Announce at start: One sentence telling the user which skill is active (transparency)
    • Format: **Announce at start:** "Using ecw:<skill-name> to <purpose>."
  2. Mode switch: Update session-state.json mode/state fields (state tracking)
    • Format: **Mode switch**: Update \session-state.json` to reflect mode ``.`

Rationalization Defense Tables (Critical skills)

For skills where LLM may self-rationalize skipping steps, include a table of:

Rationalization Pattern Why It's Wrong Correct Behavior

Apply to: risk-classifier, impl-verify, tdd, spec-challenge, writing-plans.

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 · 39 lines · 0 tokens per session scan A 6cd0ad2ee27e

Subscribe to this mod's changes

skill-files is a cursor rule published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 321 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.