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.
npx agentmods add agents/smart-ai-memory/attune-ai/help-content-explainergit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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.
[](https://agentmods.dev/agents/smart-ai-memory/attune-ai/help-content-explainer)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Local corpus first —
Globfor a.help/tree under the cwd (.help/templates/**/*.md). This is the project's own help content. - Installed attune-help templates — if no local corpus, the templates
ship inside the installed package at
**/site-packages/attune_help/templates/.Globthere. - Feature-name → path — if the user gave a feature name rather than a
path, read
summaries.jsonat 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:
Grepfor symbols, imports, function/class names, and patterns the template discusses (e.g. for a "security audit" template:eval(,subprocess,pickle, path-handling, auth checks).Globto map the relevant modules;Readthe 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.
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.
- 2d ago First seen · 78 lines · 80 tokens per session scan A cf177df7b7f7
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.
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.
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.
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime 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.
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.
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.