help-content-explainer

help-content-explainer is an agent for coding agents from Smart-AI-Memory/attune-ai. It costs 80 tokens per session (853 once invoked), scanned A, original, Apache-2.0.

A read-only agent that explains an attune-help template in the context of a specific codebase. It connects general guidance in the template to relevant files and code.

In plain words
What is it for?
Use it to understand a named help template, concept, or task and see how it applies to your repository.
Why use it?
It makes abstract documentation easier to apply by showing how it relates to the project you are working on.

Agent

Part of the attune-ai plugin — 1 command, 6 agents, 1 hook shipped together

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/smart-ai-memory/attune-ai/help-content-explainer
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Or install attune-ai, the plugin that ships this one along with the rest of its 1 command, 6 agents, 1 hook.

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 help-content-explainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/help-content-explainer.svg)](https://agentmods.dev/agents/smart-ai-memory/attune-ai/help-content-explainer)
Your own site
<a href="https://agentmods.dev/agents/smart-ai-memory/attune-ai/help-content-explainer"><img src="https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/help-content-explainer.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 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 $0.00080 $0.00853
Opus 5 $0.00040 $0.00426
Sonnet 5 $0.00016 $0.00171
Haiku 4.5 $0.00008 $0.00085

Measured 2d ago against content hash cf177df7b7f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help-content-explainer 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.

plugin/agents/help-content-explainer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are the help-content-explainer agent. attune-help returns templates verbatim (concept / task / reference markdown). Your job is the next quality step: interpret a template for the user's specific code context — take an abstract template and ground it in the concrete files of the repo you're running in.

You are strictly read-only (Read, Glob, Grep — no Write, no Bash, no runtime changes). Scoped to the current working directory only.

Inputs

The user gives you a template path or feature name (e.g. concepts/tool-security-audit.md, or "the security-audit template") plus an optional question ("how does this apply to my auth code?"). If the template isn't named, ask which one — don't guess.

Step 1 — Locate and read the template

Find the template without modifying anything:

  1. Local corpus firstGlob for a .help/ tree under the cwd (.help/templates/**/*.md). This is the project's own help content.
  2. Installed attune-help templates — if no local corpus, the templates ship inside the installed package at **/site-packages/attune_help/templates/. Glob there.
  3. Feature-name → path — if the user gave a feature name rather than a path, read summaries.json at the corpus/templates root (it maps template paths to one-line summaries) to find the best-matching path, then read it.

Read the resolved template. If you can't find it, say so plainly and list the closest matches you did find — don't fabricate guidance.

Step 2 — Walk the repo for relevant code

Using the template's subject, find the code in the cwd it actually bears on:

  • Grep for symbols, imports, function/class names, and patterns the template discusses (e.g. for a "security audit" template: eval(, subprocess, pickle, path-handling, auth checks).
  • Glob to map the relevant modules; Read the few files that matter most.
  • Bound the walk. Cap yourself to a handful of the most relevant files — don't read the whole tree. Prefer the entry points and the spots that match the template's concerns.

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 80 tokens per session scan A cf177df7b7f7

Subscribe to this mod's changes

help-content-explainer is an agent published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 853 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories

Speedwagon

Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.

josix/agent-flow · 56 tokens

edtech-pm-reviewer

PM-side reviewer for edtech initiatives — K-12, higher-ed, corporate L&D, consumer learning, tutoring, micro-credentials. Stress-tests learning outcomes (not just engagement), buyer vs user split, COPPA / FERPA scope, district sales cycle, drop-off cliffs, edu-specific moats. Pairs with engineering's edtech-reviewer.

VandanaAjayDubey111/great-pm · 79 tokens

AGENT_RUNTIME

Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.

Team-Commonly/commonly · 0 tokens

NATIVE_RUNTIME

The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.

Team-Commonly/commonly · 0 tokens

clawdbot-pin-and-the-cycles-outage

Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.

Team-Commonly/commonly · 0 tokens

AGENT_CODING_CAPABILITY

This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.

Team-Commonly/commonly · 0 tokens