sentinel

sentinel is an agent for Claude Code from Alexander-Tyagunov/magician. It costs 49 tokens per session (456 once invoked), scanned A, original, MIT.

A security-review agent that examines code changes for vulnerabilities, such as injection, missing access checks, exposed secrets, and unsafe input handling.

In plain words
What is it for?
It is for reviewing a code diff or pull request against common web-security risks, including authentication, authorization, data handling, file access, dependencies, and logging.
Why use it?
It helps find security weaknesses and attack paths that a normal code review might miss, including lower-confidence or lower-severity issues for later checking.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the magician plugin — 26 skills, 4 agents, 10 hooks shipped together

Good fit It is for reviewing a code diff or pull request against common web-security risks, including authentication, authorization, data handling, file access, dependencies, and logging.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexander-tyagunov/magician/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.

Clone the repo
git clone --depth 1 https://github.com/Alexander-Tyagunov/magician

Made for: Claude Code.

Or install magician, the plugin that ships this one along with the rest of its 26 skills, 4 agents, 10 hooks.

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/agents/alexander-tyagunov/magician/sentinel/github.svg)](https://agentmods.dev/agents/alexander-tyagunov/magician/sentinel)
Your own site
<a href="https://agentmods.dev/agents/alexander-tyagunov/magician/sentinel"><img src="https://agentmods.dev/badge/agents/alexander-tyagunov/magician/sentinel/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 sentinel

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexander-tyagunov/magician/sentinel"><img src="https://agentmods.dev/badge/agents/alexander-tyagunov/magician/sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 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 $0.00049 $0.00456
Opus 5 $0.00024 $0.00228
Sonnet 5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00046

Measured 11d ago against content hash ebe129a4b805, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

agents/sentinel.md · 47 lines

What it actually says

Sentinel Security Agent

You are a security reviewer. Your job is to find vulnerabilities and attack surfaces.

Context you receive

You do not see the prior conversation. Your spawn prompt must contain the change scope (files/diff) and goal. If the diff or target files were not provided, say NEEDS_CONTEXT: <what is missing> and stop rather than guessing.

Review Checklist (OWASP Top 10 focus)

  • No SQL injection: all queries parameterized
  • No XSS: all user output escaped, no innerHTML with user data
  • No hardcoded credentials or secrets
  • Authentication and authorization on all protected endpoints
  • Input validation at all system boundaries
  • No SSRF: user-provided URLs not fetched without allowlist
  • No path traversal: file operations don't use raw user input
  • Sensitive data not logged
  • No eval() or equivalent with user input
  • Dependencies checked for known CVEs

Report coverage, not a shortlist

Your job at this stage is recall. Report every weakness you find, including ones you are uncertain about and ones you judge low-severity. Do not filter for importance or confidence — a separate verification pass ranks and drops findings, and it can only drop what you surfaced. Withholding a real exposure because it felt minor is a miss; a finding that later gets filtered out costs nothing.

Output Format

For each finding:

SEVERITY: Critical | High | Medium | Low
CONFIDENCE: High | Medium | Low
FILE: path/to/file.ts:line
VULNERABILITY: <type>
DETAIL: <how it can be exploited>
FIX: <remediation>

End with: SENTINEL COMPLETE. Security posture: <summary>.

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. 11d ago First seen · 47 lines · 49 tokens per session scan A ebe129a4b805

Subscribe to this mod's changes

sentinel is an agent published in the GitHub repository Alexander-Tyagunov/magician (14 stars, last pushed 10d ago), licensed MIT. It adds 49 tokens to every session and 456 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

forge-reviewer

Reviews code against spec requirements and quality standards. Returns PASS or ISSUES with file:line references and severity levels. Dispatched after task implementation.

LucasDuys/forge · 33 tokens

python-data-architect

Python data pipeline (Pandas/Polars + SQLAlchemy) architecture specialist. Validates pipeline/transform/loader/writer layering, pure-function transforms, no-mutation discipline, type hint requirements, and Polars-over-Pandas guidance. Dispatch when touching pipelines, transforms, loaders, writers, or schema models.

onlygian/G-Forge · 68 tokens

python-ml-architect

Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.

onlygian/G-Forge · 59 tokens

doc-reviewer

Use proactively when documentation changes, when public exports change, or at milestone close. Read-only documentation review gate — checks docs for accuracy, currency, completeness, clarity, and volatile in-flight state against the code. Reports with file:line refs and severity, then issues DOCS READY or DOCS HOLD.…

onlygian/G-Forge · 69 tokens

angular-architect

Angular 17+ standalone components architecture specialist. Validates standalone component structure, dependency injection patterns, change detection strategy, feature module boundaries, and service layering. Dispatch when touching components, services, guards, or feature organization.

onlygian/G-Forge · 48 tokens

astro-architect

Astro architecture specialist. Validates static-first rendering decisions, client directive usage, island boundaries, content collection patterns, and import layering. Dispatch when touching pages, components, islands, or content.

onlygian/G-Forge · 43 tokens