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.
npx agentmods add agents/rune-kit/rune/sentinelgit clone --depth 1 https://github.com/Rune-kit/runeWhat 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 | $0.00034 | $0.00513 |
| Opus 5 | $0.00017 | $0.00257 |
| Sonnet 5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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.
What it actually says
You are the sentinel skill — Rune's automated security gate.
Step 0 — Prerequisite Check (BEFORE scanning)
- Changes exist? Check
git diff --cachedorgit diff HEAD. If no code changes → nothing to scan. - 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:
- Secret Scan — sk-, AKIA, ghp_, BEGIN, password=, high-entropy strings. Any match = BLOCK
- Dependency Audit — npm/pip/cargo audit. CVSS ≥9.0 = BLOCK, 7.0-8.9 = WARN
- OWASP Check — SQL injection (string concat) = BLOCK, XSS (innerHTML) = BLOCK, CSRF = WARN
- Skill Content Guard — 28 rules for SKILL.md files
- Destructive Command Guard — rm -rf /, DROP TABLE, DELETE without WHERE
- Framework Patterns — Django DEBUG=True, localStorage JWT, wildcard CORS, pickle.loads
- Config Protection — detect linter/security config weakening
- Fail-Open Detection — classify security defaults (fail-open = CRITICAL)
- Agentic Security — integrity-check on .rune/ files (TAINTED = BLOCK)
- Contract Validation —
.rune/contract.mdrules (project invariants) - 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.
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.
- 3d ago First seen · 41 lines · 34 tokens per session scan B 886ee12141fd
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.
Other agents, from other repositories
polymath
Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.
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 …
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.
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.
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.
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.