sentinel

A pre-commit security checker that looks for secrets, known code weaknesses, risky dependencies, destructive commands, and unsafe project settings. It can stop the work pipeline when it finds a blocking problem.

In plain words
What is it for?
Use it to scan changed code, dependencies, project settings, skill files, and Rune contract files before committing or continuing automated work.
Why use it?
It catches common security and safety problems before code is committed, reducing the chance of exposing secrets, introducing vulnerabilities, or deleting data by mistake.

Agent

Part of the rune plugin — 57 agents shipped together

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.

agentmods
npx agentmods add agents/rune-kit/rune/sentinel
Clone the repo
git clone --depth 1 https://github.com/Rune-kit/rune

Or install rune, the plugin that ships this one along with the rest of its 57 agents.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00034 $0.00513
Opus 5 $0.00017 $0.00257
Sonnet 5 $0.00007 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured 3d ago against content hash 886ee12141fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sentinel scanned grade B with 1 finding 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 3d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

5. **Destructive Command Guard** — rm -rf /, DROP TABLE, DELETE without WHERE

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

agents/sentinel.md · 41 lines

What it actually says

You are the sentinel skill — Rune's automated security gate.

Step 0 — Prerequisite Check (BEFORE scanning)

  1. Changes exist? Check git diff --cached or git diff HEAD. If no code changes → nothing to scan.
  2. Scope clear? Are you scanning specific files or full project? Determine scope before starting pipeline.

Only proceed after Step 0 is satisfied.

Quick Reference

Scan Pipeline:

  1. Secret Scan — sk-, AKIA, ghp_, BEGIN, password=, high-entropy strings. Any match = BLOCK
  2. Dependency Audit — npm/pip/cargo audit. CVSS ≥9.0 = BLOCK, 7.0-8.9 = WARN
  3. OWASP Check — SQL injection (string concat) = BLOCK, XSS (innerHTML) = BLOCK, CSRF = WARN
  4. Skill Content Guard — 28 rules for SKILL.md files
  5. Destructive Command Guard — rm -rf /, DROP TABLE, DELETE without WHERE
  6. Framework Patterns — Django DEBUG=True, localStorage JWT, wildcard CORS, pickle.loads
  7. Config Protection — detect linter/security config weakening
  8. Fail-Open Detection — classify security defaults (fail-open = CRITICAL)
  9. Agentic Security — integrity-check on .rune/ files (TAINTED = BLOCK)
  10. Contract Validation.rune/contract.md rules (project invariants)
  11. Six-Gate Finding Validation — every finding must pass: evidence, reachability, real impact, PoC plausibility, math/bounds, environment

Verdict: BLOCK (any BLOCK finding) / WARN / PASS

Critical Rules:

  • MUST NOT deploy with CRITICAL security findings (hard gate)
  • Contract violations skip Six-Gate validation (they're hard gates)
  • "Internal tool" is NOT an excuse to skip security
  • Escalate to opus for deep audit (3+ trust boundaries, auth/crypto)

Read skills/sentinel/SKILL.md for the full specification including organization policy enforcement.

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. 3d ago First seen · 41 lines · 34 tokens per session scan B 886ee12141fd

Subscribe to this mod's changes

sentinel is an agent published in the GitHub repository Rune-kit/rune (84 stars, last pushed 17d ago), licensed MIT. It adds 34 tokens to every session and 513 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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

polymath

Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.

pjt222/agent-almanac · 25 tokens

insistir-reviewer

Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …

JairoTorregrosa/jaiskills · 76 tokens

insistir-researcher

Research agent for insistir orchestration. Researches best practices, framework documentation, and codebase patterns. Read-only — cannot edit or write files. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 50 tokens

insistir-learnings-researcher

Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 68 tokens

insistir-worker

Implementation agent for insistir multi-agent orchestration. Implements a task or applies review fixes, commits, reports to lead. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 42 tokens

askit-quality-grader

Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outputs. Use when delegating a behavioral evaluation - the opt-in LLM-judge role behind askit-evaluate's behavioral mode, distinct from the deterministic conformance core.

product-on-purpose/agent-skills-toolkit · 60 tokens