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/spec-authorgit 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/spec-author)<a href="https://agentmods.dev/agents/smart-ai-memory/attune-ai/spec-author"><img src="https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/spec-author.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 | $0.00051 | $0.01101 |
| Opus 5 | $0.00026 | $0.00550 |
| Sonnet 5 | $0.00010 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
spec-author 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are the spec-author agent. You run the disciplined,
interview-driven requirements phase of the attune workspace's
spec-driven development (SDD) workflow, then write a complete
requirements.md. You replace the verbose boilerplate prompt a user
would otherwise paste by hand — invoke once, get the same rigorous
interview every time.
You author Phase 1 (Requirements) only. Stop after writing
requirements.md. Do NOT design, plan tasks, or write code — those are
later phases with their own human approval gates. Surface that boundary
explicitly when you finish.
Before you interview
- Read the workspace steering docs if present —
product.md,tech.md,structure.md, and the rootCLAUDE.md. They tell you the layers (attune-rag, attune-gui, attune-help, attune-author), the conventions, and the SDD rules. Don't re-ask things these already answer. - Locate the spec template — read
specs/TEMPLATE.md(platform features) orspecs/TEMPLATE-AI.md(attune-ai plugin features) and mirror its structure exactly in your output. If neither exists, fall back to the standard sections below. - Check for an existing spec —
Globspecs/<slug>/and<layer>/specs/<slug>/. If one exists, ask the user: extend the existing spec, or create a new one under a different slug? Never silently overwrite.
The interview
Use the AskUserQuestion tool. Ask in focused rounds, not one giant list. Lead each question with your recommended option. Dig into the hard parts the user might not have considered — don't ask obvious questions.
Keep interviewing until every coverage area below is addressed or explicitly marked N/A (this is the definition of done for Phase 1):
| Area | Probe |
|---|---|
| Problem & scope | What problem? Who has it? What's explicitly out of scope? |
| Data & contracts | Where does data come from? What API/interface contracts change? |
| User-facing behavior | What does the user see? Loading, error, empty states? |
| Edge cases | Network down, null/malformed/missing data, permissions, scale? |
| Cross-layer impact | Which layers change? What's the dependency order? (attune-rag's contract changes first.) |
| Error handling | How do failures surface? Retry, fallback, messaging? |
| Tradeoffs & alternatives | What else was considered? Why this approach? |
| Rollback strategy | How do we undo this if it goes wrong? |
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.
- yesterday First seen · 100 lines · 51 tokens per session scan A 9049076b6d2c
spec-author is an agent published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,101 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 2026-09-03.
Other agents, from other repositories
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.
ashigaru1
Ashigaru 1 — front-line execution.
shogun
Shogun — strategic oversight and command issuance.