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 skills/smart-ai-memory/attune-ai/fixnpx skills add Smart-AI-Memory/attune-ai --skill fixgit 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/skills/smart-ai-memory/attune-ai/fix)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/fix"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/fix.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 | $0.01213 |
| Opus 5 | $0.00026 | $0.00607 |
| Sonnet 5 | $0.00010 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
fix 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix (guided intake)
IMPORTANT: Start your response by telling the user:
Fix — Composing an outcome-first fix: goal, scope, and verification probes, then a preview before anything runs.
What It Does
Interactive intake for attune fix (the outcome-first Fix surface,
docs/specs/outcome-first-fix/): one form gathers the goal, the
--scope the diff must stay confined to, and the --probe
commands that verify the fix — with scope and probe options DERIVED
from the working tree (changed paths and matching test files), not
typed from memory. The composed CLI command is previewed before any
execution; the receipt independently verifies every probe.
Relationship to /fix-test: that skill diagnoses and fixes a
FAILING TEST in-session. This skill drives the attune fix CLI
contract — goal + scope + probes + receipt — for any code fix.
Neither replaces the other.
Step 1 — Derive candidates and build the form
python -m attune.elicitation.fix_intake
The JSON payload contains a validated form definition
(attune.elicitation.fix_intake.build_fix_intake_form) plus the
derived scopes and probes lists. Changed paths lead; on a clean
tree the candidates fall back to recently-touched directories from
git history, so pickers render in either state — empty lists mean
the repo has no usable history at all. If the user's invocation
already stated the goal, carry it into the request field as the
default rather than asking again.
Step 2 — Render the form (communication grammar)
Render ONE form — request, scope, probes. The enhanced
widget is the DEFAULT surface: build the FormSchema from the
Step 1 payload, route it through select_form_surface, and when
it returns "widget" render form_to_widget_html(form) on the
widget surface — answers post back as an
__elicitation_response__ payload; parse them with
collect_form_response. Carry an already-stated goal into the
request field as its default.
Fall back to AskUserQuestion ONLY when no widget surface exists
(batch the questions; metadata.source containing "form" opts
into the batch). Never ask these as sequential single questions —
and never hand-write the ask turn without consulting
select_form_surface first: steering that names the fallback
concretely gets the fallback executed. When a field came back with
no derived options it is free text — accept a path or command, do
not invent options.
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.
- 5d ago First seen · 120 lines · 51 tokens per session scan A b052d455125a
fix is a skill 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 1,213 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
story-setup
网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录,支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。.
novel-writing-assets
查看、启用、停用、组合、绑定、试写和重新编译 novel-studio 的长期写法资产。触发:「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」。.
novel-rewrite
通过 novel-studio pipeline 的 rewrite 阶段按评审反馈逐章 Writer 重写,会改动章节原文。触发:「按评审改写」「重写这几章」「根据意见润色正文」,在 novel-review 之后据反馈落地修改时使用。.