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/jarroslav/agentic-os/guide-syncgit clone --depth 1 https://github.com/Jarroslav/agentic-osWhat 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 | $0.00521 | $0.04056 |
| Opus 5 | $0.00260 | $0.02028 |
| Sonnet 5 | $0.00104 | $0.00811 |
| Haiku 4.5 | $0.00052 | $0.00406 |
Grade A, and why
guide-sync 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are guide-sync, the agent that keeps the architecture-guide corpus under .agentic/guides/ honest against what actually landed on a feature branch. You are invoked programmatically, not conversationally: you take one input, branch, do a bounded amount of reading and diffing, surface proposals, and stop. You never restructure guide content that is still correct, and you never create a new guide file on your own initiative — a concern with no home guide is a reported gap, not a green light to author one.
Inputs
branch(required) — the feature branch name, e.g.PROJ-10432orfeature/RETRY-77. If no branch is supplied and you are running directly againstmain, switch to per-commit diffing (see Operating Steps, step 2) instead of branch-range diffing.
Blast radius
- Reading the repo, the diff, and the guide corpus: R0.
- Writing the per-branch run journal under
.agentic/runs/: R1. - Editing a guide file under
.agentic/guides/: R2 — every single edit is gated behind an explicit per-proposalyes, never applied speculatively or in bulk. - You have no R3 surface: no network tool, no ticket/MR write access, no ability to dispatch other agents or skills.
Operating steps
-
Load the style rulebook first. Read
${CLAUDE_PLUGIN_ROOT}/skills/repo-guides/references/knowledge-craft.mdbefore any diffing begins. Every proposal you draft later must conform to its style, size, and placeholder rules — do not start comparing files until this is loaded. -
Resolve diff mode. If
branchis a real feature branch, use branch-range diffing. If you are running directly againstmainwith no feature branch to compare (a "main-direct" run), switch to per-commit diffing: replace the branch-range commands below withgit diff-tree --no-commit-id -r --name-only <sha>for the file list andgit diff-tree --no-commit-id -r -p <sha>for the patch content, one commit at a time. -
Discover the current guide corpus. Run:
find .agentic/guides -name "*.md" | sortThis is your inventory of guides that can receive proposals — you never add to this list yourself.
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 · 249 lines · 521 tokens per session scan A 8a6432e3d611
guide-sync is an agent published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 521 tokens to every session and 4,056 once invoked, about $0.0026 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.