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/Rune-kit/runeWrote 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/rune-kit/rune/scope-guard)<a href="https://agentmods.dev/agents/rune-kit/rune/scope-guard"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/scope-guard/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/rune-kit/rune/scope-guard"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/scope-guard.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 | $0.00041 | $0.00246 |
| Opus 5.5 | $0.00016 | $0.00098 |
| Sonnet 5.5 | $0.00008 | $0.00049 |
| Haiku 4.5 | $0.00004 | $0.00025 |
Grade A, and why
scope-guard 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 1mo 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 scope-guard skill — Rune's scope creep detector.
Quick Reference
Workflow:
- Load plan from TodoWrite or
.rune/progress.md - Run
git diff --stat+git diff --cachedto see actual changes - Classify each file: IN_SCOPE (planned) vs OUT_OF_SCOPE (unplanned)
- Flag test files, config changes, lock files as natural dependencies (not creep)
- Classify: IN_SCOPE / MINOR CREEP (1-2 files) / SIGNIFICANT CREEP (3+ files)
- Report with recommendations
Critical Rules:
- Compare against stated scope (not just file count)
- Flag specific files with reasoning
- Advisory only — allow user override (not authoritarian)
Read skills/scope-guard/SKILL.md for the full specification.
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.
- 1mo ago First seen · 26 lines · 41 tokens per session scan A 85a07e80a5d7
scope-guard is an agent published in the GitHub repository Rune-kit/rune (86 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 246 once invoked, about $0.0002 per session on Opus 5.5. 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
implement-intake
PRFlow Phase 1 intake: issue requirements, acceptance criteria, resume/workpad preparation and dependency checks.
branch-setup
PRFlow implement's Phase 1.4 branch-setup agent — invokes the deterministic setup helper and records its result.
implement-finalization
Use when implement reaches Phase 4 or resumes unfinished finalization.
review-fix-worker
PRFlow implement Phase 3.3 worker: runs the review-and-fix loop in an isolated context and returns a validated handoff.
orc-stack-analyzer
Investigator role — analyzes a too-big branch's diff and proposes how to split it into a stack of smaller, logically-coherent PRs, emitting a JSON plan (slices + non-interactive rebase plan) for the orchestrator to execute. Used by /orc:stack-pr --smart when commits are too messy for the default commit-based strategy.…
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 …