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 commands/majiayu000/vibeguard/skill-validategit clone --depth 1 https://github.com/majiayu000/vibeguardWrote 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/commands/majiayu000/vibeguard/skill-validate)<a href="https://agentmods.dev/commands/majiayu000/vibeguard/skill-validate"><img src="https://agentmods.dev/badge/commands/majiayu000/vibeguard/skill-validate.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00603 |
| Opus 5 | $0.00009 | $0.00302 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
VibeGuard: Skill Validate 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 6d 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
Core Concept
- A proposed skill is an intervention, not just documentation.
- Accept it only after measuring
without_skillvswith_skillon recorded scenarios. - Keep facts separate from judgment: repairs, regressions, stale evidence, and unrelated-task regressions are explicit.
Minimum JSONL Schema
Each nonblank line in the baseline or held-out file is one scenario:
{
"scenario_id": "incident-1",
"scenario_type": "target | unrelated",
"without_skill": {"outcome": "success | failure"},
"with_skill": {"outcome": "success | failure"},
"scored_against_agent": "claude-opus-4-7",
"scored_at": "2026-05-18",
"notes": "optional human judgment notes"
}
Steps
- Use
/vibeguard:learnor a draft PR to propose aSKILL.md. - Record 3-5 scenarios:
- At least one motivating incident the skill should repair.
- At least two unrelated tasks the skill should not affect.
- Optional held-out scenarios for the final verdict.
- Run:
python3 ~/vibeguard/scripts/skill_validate.py \ --proposed-skill path/to/SKILL.md \ --baseline-trajectories path/to/baseline.jsonl \ --held-out path/to/held-out.jsonl \ --current-agent <agent-or-model-id> - Treat the verdict as the gate:
pass:repair > regression, at least one repair, no regressions.needs_justification: repair beats regression but at least one regression needs a written trade-off.advisory: unrelated task regression exists; do not install as a hard instruction.stale: evidence was scored against a different or too-old agent/model.fail: no demonstrated repair, or regressions are greater than/equal to repairs.
- Attach the emitted artifact path from
${VIBEGUARD_HOME:-${HOME}/.vibeguard}/artifacts/skill-validate/<project>/to the PR or final answer.
Rules
- Do not accept a new or changed skill on senior judgment alone.
- Do not hide regressions in summary prose; report the count and affected scenario IDs.
- Docs-only typo fixes can opt out; changes to constraints or decision rules need this gate.
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.
- 6d ago First seen · 57 lines · 18 tokens per session scan A 4821c284a18b
VibeGuard: Skill Validate is a command published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 603 once invoked, about $0.0001 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 commands, from other repositories
patterns
List makoto's integrity pattern catalog (read-only).
show
Read makoto's results ledger by key (read-only).
status
Show makoto's integrity-guardrail state (read-only).
claudemd-design-adopt
Generate a thin, fact-based DESIGN.md from a UI project's real design-token sources and wire it into project CLAUDE.md. Use when (1) the user asks to configure design specs / 配置设计规范 / 设计规范 for agents, (2) UI sessions keep inventing colors or spacing instead of using the project's existing tokens, (3) a UI project…
claudemd-refresh
Refresh the installed claudemd plugin to the latest released version in one shot (marketplace update → uninstall → install via the claude CLI). Use when the SessionStart banner reports a newer version, or /claudemd-doctor flags a stale plugin cache. Restart Claude Code afterwards — spec + manifest then sync…
claudemd-update
Sync /.claude/CLAUDE.md with the plugin-cache shipped spec. Shows diff summary; user chooses apply-all or cancel.