attune-ai: Skill for Claude Code

.agents/skills/author-feature/SKILL.md

author-feature is a skill for Claude Code, Codex from Smart-AI-Memory/attune-ai. It costs 52 tokens per session (2,180 once invoked), scanned A, original, Apache-2.0.

A single-source feature-page authoring workflow for a code project. It creates one checked master document and projects it into help and documentation pages.

In plain words
What is it for?
It helps write feature documentation, verify referenced code symbols, run documentation checks, and produce the related help and docs pages.
Why use it?
It keeps related documentation consistent and catches claims or references that do not match the live code.

Skill for Claude CodeCodex

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

This is Smart-AI-Memory/attune-ai's own configuration. It tells Claude Code and Codex how to work on attune-ai 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 attune-ai configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/project_features.py <feature> --dry-run.

Reuse

Borrowing it

Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. 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/Smart-AI-Memory/attune-ai/main/.agents/skills/author-feature/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

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 author-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/author-feature/github.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/author-feature)
Your own site
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/author-feature"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/author-feature/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for author-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/author-feature"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/author-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,180 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 87
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00052 $0.02180
Opus 5 $0.00026 $0.01090
Sonnet 5 $0.00010 $0.00436
Haiku 4.5 $0.00005 $0.00218

Measured 9d ago against content hash 7e3ddf3cbf65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

author-feature 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 9d 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/author-feature/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Author-feature — single-source authoring, verified

IMPORTANT: Start your response by telling the user:

Author-feature — I'll author a single-source master for this feature, grounding every claim in live code and running the gates as I go, then project it to the help kinds + docs pages. No LLM generation, no API credits.

This skill makes the driving session a disciplined author of a single-source master (content/features/<feature>.md). One master projects deterministically to 10 .help kinds + 4 docs/ pages — no generator, no API. The empirical result that motivates it: the session is a superior polish layer to an LLM pass and the only one that catches correctness bugs (PR #1188). The risk it manages: a master is a single point of failure, so verification is the spine — grep the symbol before you write it, run the audit before you commit, fix the master not the output.

This is judgment, not plumbing. It calls the deterministic tools (the in-repo projector, the audits); it never re-implements them and never emits prose for blind rubber-stamping.

The flow

locate/scaffold  →  author section-by-section (grounded in code)
                 →  verify continuously  →  project  →  preview  →  commit

Step 1 — locate or scaffold the master

The master lives at content/features/<feature>.md. If it exists, you're revising — open it. If not, create it by copying a canonical projected page for structure — e.g. content/features/security-audit.md — then replacing its content. Do not invent the layout; the projector expects a fixed section contract (below).

Frontmatter (required):

---
feature: <slug>
summary: <one line>
tags: [<tag>, <tag>]
source_globs:
  - src/attune/workflows/<feature>.py
nav:
  help: <slug>
  mkdocs:
    how-to: how-to/<slug>
    architecture: architecture/<slug>
    reference: reference/<slug>
---

Declare how-to / architecture / reference but not tutorial: the projector drops tutorial (a guided tutorial resists pure section projection — it stays hand-authored).

Read the full file on GitHub · 202 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. 9d ago First seen · 202 lines · 52 tokens per session scan A 7e3ddf3cbf65

Subscribe to this mod's changes

author-feature is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 2,180 once invoked, about $0.0003 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.