sync-ops-knowledge

sync-ops-knowledge is a skill for Claude Code from Abilityai/abilities. It costs 59 tokens per session (1,915 once invoked), scanned D, original, MIT.

A tool for keeping operations documentation aligned with recent code changes.

In plain words
What is it for?
It reviews recent Git commits and proposes updates to files such as CLAUDE.md or other agent instructions without changing application code.
Why use it?
It helps prevent deployment and maintenance instructions from becoming outdated when configuration, APIs, services, or database schemas change.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the utilities plugin — 7 skills shipped together

Good fit It reviews recent Git commits and proposes updates to files such as CLAUDE.md or other agent instructions without changing application code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abilityai/abilities/sync-ops-knowledge
Install

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.

Any agent
npx skills add Abilityai/abilities --skill sync-ops-knowledge
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code.

Or install utilities, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for sync-ops-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/abilities/sync-ops-knowledge/github.svg)](https://agentmods.dev/skills/abilityai/abilities/sync-ops-knowledge)
Your own site
<a href="https://agentmods.dev/skills/abilityai/abilities/sync-ops-knowledge"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/sync-ops-knowledge/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.

agentmods 80×15 button for sync-ops-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/abilityai/abilities/sync-ops-knowledge"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/sync-ops-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,915 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01915
Opus 5.5 $0.00024 $0.00766
Sonnet 5.5 $0.00012 $0.00383
Haiku 4.5 $0.00006 $0.00192

Measured 1mo ago against content hash 014683ace04a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

sync-ops-knowledge scanned grade D with 2 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

SSH_KEY=${SSH_KEY:-"~/.ssh/id_rsa"}

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/ 2>/dev/null || ls skills/ 2>/dev/null
plugins/utilities/skills/sync-ops-knowledge/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Ops Knowledge

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. sync-ops-knowledge vX.Y — recent: <summary>. Then proceed.

Review recent changes in a managed codebase and update the ops agent's documentation to reflect new operational requirements. Ensures the agent stays current without modifying application code.


Use Case

An ops agent manages a service it doesn't control — it can't modify the source code, but it needs to know:

  • New environment variables that must be configured on deploy
  • Changed API endpoints that health checks or scripts rely on
  • New Docker services or removed services
  • Schema migrations that affect backup/restore procedures
  • New configuration options the agent should advise on

This skill reviews git history and proposes documentation updates.


Prerequisites

# Path to the managed codebase (read-only — never modify)
MANAGED_REPO=${MANAGED_REPO:-""}  # e.g. ~/app or a local clone

# Optional: days of history to review (default: 7)
SINCE_DAYS=${SINCE_DAYS:-7}

Or SSH-based review of a remote repo:

SSH_HOST=${SSH_HOST:-""}
SSH_USER=${SSH_USER:-"ubuntu"}
SSH_KEY=${SSH_KEY:-"~/.ssh/id_rsa"}
APP_PATH=${APP_PATH:-"~/app"}
RUN="ssh -i $SSH_KEY $SSH_USER@$SSH_HOST"

Parse $ARGUMENTS for --since=Nd or a repo path.


Step 1: Get Recent Commits

Local repo:

cd $MANAGED_REPO
git log --oneline --since="${SINCE_DAYS} days ago" | head -50

Remote repo:

$RUN "cd $APP_PATH && git log --oneline --since='${SINCE_DAYS} days ago' | head -50"

Display commit list to user. If no commits in the window, say so and exit.


Step 2: Analyze Each Commit for Ops Impact

For each commit, check what files changed:

# Local
git show --stat [commit-hash]

# Remote
$RUN "cd $APP_PATH && git show --stat [commit-hash]"

Flag commits that touch ops-relevant files:

Read the full file on GitHub · 273 lines

Changes

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.

  1. 1mo ago First seen · 273 lines · 59 tokens per session scan D 014683ace04a

Subscribe to this mod's changes

sync-ops-knowledge is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,915 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (reaches for credential files, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Related

Other skills, from other repositories