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/safeguard)<a href="https://agentmods.dev/agents/rune-kit/rune/safeguard"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/safeguard/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/safeguard"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/safeguard.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 | $0.00032 | $0.00275 |
| Opus 5.5 | $0.00013 | $0.00110 |
| Sonnet 5.5 | $0.00006 | $0.00055 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
safeguard 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 safeguard skill — Rune's pre-refactoring safety net builder.
Quick Reference
Workflow:
- Identify Module Boundaries — via scout: public functions, consumers, dependencies, tests
- Write Characterization Tests — capture CURRENT behavior (even buggy); cover every public function
- Add Boundary Markers — @legacy, @bridge, @do-not-touch inline comments
- Config Freeze — copy tsconfig, eslintrc, package-lock to .rune/
- Create Rollback Point — git tag
rune-safeguard-<module> - Verify — tests MUST pass on current unmodified code
Hard Gates:
- Characterization tests MUST pass on unmodified code — if they fail, safety net is broken
- MUST cover critical paths identified by autopsy
- Tests must be meaningful — fail if module is deleted/changed
- MUST complete before surgeon touches any code
Read skills/safeguard/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 · 27 lines · 32 tokens per session scan A fc11d3a2d014
safeguard is an agent published in the GitHub repository Rune-kit/rune (86 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 275 once invoked, about $0.0001 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
qa
Quality assurance specialist for testing, bug hunting, security review, and validation. Use proactively after code changes, before deployments, or when verifying correctness.
qa-engineer
Designs test strategies and automates quality assurance. Expert in testing frameworks, CI integration, coverage. Uses evidence-based validation.
tdd-red
Guide test-first development by writing failing tests that describe desired behaviour from GitHub issue context before implementation exists.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
sealer
The one broad run. Spawn after the review rounds settle and before the draft pull request is marked ready: it runs the repository's broad command and the plugin's own checks through broad-gate, reports what they said, and writes the last round record's Broad gate cell. It judges nothing.