sentinel

sentinel is a skill for Claude Code from supportersimulator/3-surgeons. It costs 9 tokens per session (1,431 once invoked), scanned A, original, MIT.

A complexity scanner for plans, code changes, commit messages, and other work descriptions. It checks several risk areas to reveal problems you may have missed.

In plain words
What is it for?
Use it before major changes, after feature work, or periodically on important files and modules. It can also signal when a deeper review is needed.
Why use it?
It helps spot hidden complexity before or after a change, so risky work can be reviewed earlier.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the 3-surgeons plugin — 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server shipped together

Good fit Use it before major changes, after feature work, or periodically on important files and modules. It can also signal when a deeper review is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supportersimulator/3-surgeons/sentinel
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 supportersimulator/3-surgeons --skill sentinel
Clone the repo
git clone --depth 1 https://github.com/supportersimulator/3-surgeons

Made for: Claude Code.

Or install 3-surgeons, the plugin that ships this one along with the rest of its 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server.

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 sentinel

README.md
[![agentmods](https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/sentinel.svg)](https://agentmods.dev/skills/supportersimulator/3-surgeons/sentinel)
Your own site
<a href="https://agentmods.dev/skills/supportersimulator/3-surgeons/sentinel"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/sentinel.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00009 $0.01431
Opus 5 $0.00005 $0.00715
Sonnet 5 $0.00002 $0.00286
Haiku 4.5 $0.00001 $0.00143

Measured 7d ago against content hash b4785611847a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sentinel 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.

skills/sentinel/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sentinel

When to Run

The Sentinel scans content for complexity indicators across multiple dimensions (vectors). It answers the question: "What risks am I not seeing?" Run it:

  • Before major changes -- scan the diff or plan description to surface hidden risks
  • After feature completion -- scan the implementation to catch complexity you introduced
  • Periodic scans -- scan key files or modules to monitor complexity drift over time
  • Before cross-examination -- if sentinel flags high risk, escalate to full cross-exam

Do NOT use for: health checks (use probe), claim validation (use consensus), or infrastructure verification (use gains-gate).

How to Invoke

CLI

3s sentinel "Refactoring the authentication module to use JWT tokens with Redis-backed session storage and a new OAuth2 provider integration"

MCP Tool

sentinel_run(content="Refactoring the authentication module to use JWT tokens with Redis-backed session storage and a new OAuth2 provider integration")

The content parameter is the text to scan -- it can be a description of planned work, a code diff, a commit message, or any text that describes what you are doing.

How It Works

Complexity Vectors

The Sentinel evaluates content against a set of complexity vectors. Each vector has:

Property Purpose
keywords Terms to search for in the content (case-insensitive)
risk_score Severity weight from 0.0 to 1.0
noise_threshold Maximum keyword hits before the vector is discarded as noise

Default Vectors

ID Vector Keywords Risk Score
CV-001 Authentication complexity auth, token, jwt, oauth, session 0.7
CV-002 Database schema changes migration, schema, alter table, index 0.6
CV-003 API surface changes endpoint, route, api, rest, graphql 0.5
CV-004 Security concerns injection, xss, csrf, vulnerability, exploit 0.9
CV-005 Performance impact cache, latency, throughput, bottleneck, n+1 0.6
CV-006 Concurrency issues lock, mutex, race condition, deadlock, thread 0.8
CV-007 External dependencies api key, third-party, vendor, sdk, external 0.5
CV-008 State management state, redux, context, global, singleton 0.4

Read the full file on GitHub · 161 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. 7d ago First seen · 161 lines · 9 tokens per session scan A b4785611847a

Subscribe to this mod's changes

sentinel is a skill published in the GitHub repository supportersimulator/3-surgeons (2 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 1,431 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

gh-pr-review

Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…

CherryHQ/cherry-studio · 147 tokens

review-spd

Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing…

zhu1090093659/deepseek-pp · 72 tokens

karpathy-guidelines

A set of coding guidelines based on observations about common mistakes made by language models. It emphasizes simple solutions, small targeted edits, clear assumptions, and checkable results.

itmisx/deepx-code · 55 tokens

gh-cli

Patterns for invoking the GitHub CLI (gh v2.100.0+) from agents. Use when the task mentions GitHub, gh, pull requests/PRs, issues, releases, gists, Actions/workflow runs, forks, repo cloning, reviews, or you need exact gh commands. Covers pagination, repo targeting, search vs list, discussions, projects, rulesets…

znlgis/my-opencode-deepseek-config · 88 tokens

code-review

A single-pass review method for examining a code change, branch, or pull request. A pull request is a proposed change for review before it is merged into a shared codebase.

znlgis/my-opencode-deepseek-config · 75 tokens

simplify

Behavior-preserving code simplification — reduce complexity without changing what the code does. Use when the task mentions "simplify", "reduce complexity", "too clever", "hard to read", "reduce nesting", or after a feature lands and the code needs polishing. Oracle analyzes (read-only), light-orchestrator applies the…

znlgis/my-opencode-deepseek-config · 70 tokens