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.
git clone --depth 1 https://github.com/Alexander-Tyagunov/magicianWrote 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/agents/alexander-tyagunov/magician/sentinel)<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.
<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>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 | $0.00049 | $0.00456 |
| Opus 5 | $0.00024 | $0.00228 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
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.
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>.
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.
- 11d ago First seen · 47 lines · 49 tokens per session scan A ebe129a4b805
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.
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.
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.
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.
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.…
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.
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.