AutoSaddler is a system that improves LLM-agent harnesses by diagnosing execution traces and applying structured changes to prompts, tools, middleware, and agent-loop logic. It evaluates candidate updates for their ability to generalize beyond the traces that motivated them. The catalogue add-ons represent workflows for using AutoSaddler.
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 skills add microsoft/AutoSaddler --skill capability-patchgit clone --depth 1 https://github.com/microsoft/AutoSaddlerWrote 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/microsoft/autosaddler/capability-patch)<a href="https://agentmods.dev/skills/microsoft/autosaddler/capability-patch"><img src="https://agentmods.dev/badge/skills/microsoft/autosaddler/capability-patch/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.
<a href="https://agentmods.dev/skills/microsoft/autosaddler/capability-patch"><img src="https://agentmods.dev/badge/skills/microsoft/autosaddler/capability-patch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 2 findings, up to low
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 →
- low Excessive Agency · line 60 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
- low Excessive Agency · line 130 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 5.1 | $0.00034 | $0.01683 |
| Opus 5.5 | $0.00014 | $0.00673 |
| Sonnet 5.5 | $0.00007 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
capability-patch 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 1mo 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Patch
Overview
A capability patch expands the agent's capabilities — by adding new tool methods, exposing new parameters, fixing tool implementations, or removing infrastructure limitations. These changes let the agent do things it could not do before.
Key distinction from steering patches: A capability patch changes
executable code — tool methods, parameters, implementation logic, or
infrastructure. A steering patch only changes text the agent reads
(docstrings, prompts, hooks) without modifying any code. The outer loop
selects which skill to use based on the current phase: capability
phase uses this skill, steering phase uses steering-patch.
When to Use
Based on the diagnosis results, generate a patch that resolves the identified root cause. Typical root causes addressable by capability patches:
| Root Cause Category | Signal | Example |
|---|---|---|
| Missing capability | No tool exists for the required action | Agent needs to search emails by date range but no such tool exists |
| Tool bug | Tool exists but produces wrong results | search_contacts returns empty for valid queries due to case-sensitive matching |
| Insufficient parameters | Tool exists but lacks needed arguments | Agent needs to filter by sender but the search tool only accepts keyword |
| Missing agent loop logic | Agent loop lacks a preprocessing step, reminder, or context-injection logic | No budget reminder causes agent to exhaust iterations without wrapping up; no environment summary injection at start leaves agent unaware of available data |
| Infrastructure issue | Infrastructure limits prevent success | Agent hits the iteration budget on multi-step tasks |
Workflow
Step 1: Consult History
Before writing any code, check what has been tried before:
# Full patch history: diffs, reflections, lessons (good/bad patterns)
evo-dag show history
# Per-scenario history: prior root causes and attempted fixes
evo-dag show scenario <scenario_id>
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.
- 1mo ago First seen · 190 lines · 34 tokens per session scan A 7f46ed1cdc0a
capability-patch is a skill published in the GitHub repository microsoft/AutoSaddler (243 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 1,683 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…