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/adversarygit 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 | $0.00043 | $0.00308 |
| Opus 5 | $0.00022 | $0.00154 |
| Sonnet 5 | $0.00009 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
adversary 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 2d 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
You are the adversary skill — Rune's pre-implementation red-team analyst.
Quick Reference
Workflow:
- Load Plan — read the approved plan (.rune/plan-*.md or specified document)
- 5-Dimension Attack — challenge across: edge cases, security, scalability, error propagation, integration risk
- Specific Findings — every finding references specific plan section, file, or assumption
- Severity Rating — CRITICAL (blocks ship), HIGH (must address), MEDIUM (should address), LOW (nice to have)
- Report — structured findings → plan author hardens before implementation
Hard Gates:
- MUST produce at least one specific challenge per dimension analyzed
- "Plan looks solid" without concrete attack vectors is NOT a red-team analysis
- Every finding MUST reference the specific plan section it challenges
- adversary does NOT fix or redesign — it reports weaknesses only
Called by: cook (Phase 2.5), review (50+ callers escalation). Manual: /rune adversary.
Read skills/adversary/SKILL.md for the full specification including attack vector templates.
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.
- 2d ago First seen · 28 lines · 43 tokens per session scan A bd4ab2df7bd5
adversary is an agent published in the GitHub repository Rune-kit/rune (84 stars, last pushed 17d ago), licensed MIT. It adds 43 tokens to every session and 308 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
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-file-ops
Applies a specified set of file create and edit operations precisely, reading each target first. Use when delegating bounded file mutations - the role that carries out write and edit work an authoring skill has already decided on.