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 history-analysisgit 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/history-analysis)<a href="https://agentmods.dev/skills/microsoft/autosaddler/history-analysis"><img src="https://agentmods.dev/badge/skills/microsoft/autosaddler/history-analysis.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Output Handling · line 3 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00027 | $0.01652 |
| Opus 5 | $0.00014 | $0.00826 |
| Sonnet 5 | $0.00005 | $0.00330 |
| Haiku 4.5 | $0.00003 | $0.00165 |
Grade A, and why
history-analysis 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 7d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
History Analysis
Overview
As iterations accumulate, the output of evo-dag show history grows too
large to read in a single terminal command. Naively piping through
head -200 or tail -200 discards critical information — early
iterations' lessons are lost with tail, and recent results are lost
with head. This skill provides a structured methodology to analyze
the complete history using targeted CLI commands, producing a focused
summary of what matters for the current iteration.
When to Use
At the start of every session (Session 0, 1, and 2) before any other work. The history analysis provides the context needed for informed decisions — skipping it leads to repeated mistakes, redundant patches, and missed lessons.
The Problem with Truncation
Do NOT pipe evo-dag show history through head, tail, or any
truncation command. This loses information:
head -N: Loses all recent iterations' results and reflectionstail -N: Loses early iterations' foundational lessons and patterns- Increasing the number (
head -300,tail -500) is a losing battle — the history grows every iteration
History Analysis Procedure
Step 1: Quick Orientation
Start with small, complete outputs to establish context:
# DAG topology and best candidate (always small output)
evo-dag summary
# DAG lineage visualization (always small output)
evo-dag show lineage
From this, note:
- How many iterations have been run
- Which candidate has the best dev score
- The current lineage path
Step 2: Full History via File Redirect
Redirect the full history to a temporary file and read it with file tools. This avoids terminal output truncation entirely:
evo-dag show history > /tmp/evo_history.txt
Then read the file in sections using file reading tools (e.g., cat with
line ranges, or IDE file reading). This lets you see the complete
history regardless of length.
Read the file in manageable sections:
- Start from the beginning to understand early foundational changes
- Read the end to see the most recent iterations
- Search for specific patterns or scenario IDs as needed
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.
- 7d ago First seen · 187 lines · 27 tokens per session scan A ff5883e08b34
history-analysis is a skill published in the GitHub repository microsoft/AutoSaddler (177 stars, last pushed 13d ago), licensed MIT. It adds 27 tokens to every session and 1,652 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…