Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ooooooooooooooooooop/agent-toolsnpx agentmods add skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-reviewWrote 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/skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-review)<a href="https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-review"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-review/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/skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-review"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/personal-ai-operations-review.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 | $0.00140 | $0.01681 |
| Opus 5 | $0.00070 | $0.00840 |
| Sonnet 5 | $0.00028 | $0.00336 |
| Haiku 4.5 | $0.00014 | $0.00168 |
Grade A, and why
personal-ai-operations-review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal AI 运维复查
适用范围
用于已经完成建设、进入 OPERATIONS MODE 的 Personal AI Infrastructure。目标是回答“系统现在是否正常、哪些问题需要人处理、哪些只是已知外部阻塞”。
优先复用现有 Control Plane、Governance、Durability、Memory、Model/Trace、Harness Adapter 与 Personalization Calibration 的真实输出；不要重新实现底层检查。
不适用
- 不用于设计新的 Architecture Phase、重构 Control Plane、替换 MemoryProvider 或新增基础设施。
- 不用于直接批准 model admission、修改 routing/default model/preference、删除 provider/plugin/memory、清 Git 历史或处理其他 canonical mutation。
- 不把
BLOCKED/DEGRADED自动视为系统失败；先判断它是否是治理系统正确暴露的真实约束。 - 用户明确要求实施某个 change 时，先转入既有
Need → Impact → Proposal → Implementation → Verification → Regression流程，不在本 Skill 内静默执行。 - 不在普通任务中自动执行完整巡检。
核心契约：Evidence Freshness & Cause-aware Classification
1. Evidence Freshness 契约
每个运维域必须同时输出：
status:HEALTHY/DEGRADED/BLOCKED/UNKNOWNevidence_state:CURRENT/LAST_KNOWN/UNAVAILABLE
语义：
- CURRENT：本轮成功执行真实检查。
- LAST_KNOWN：本轮实时检查不可用/失败，只能读取历史 verified evidence / baseline report。
- UNAVAILABLE：既无当前证据，也没有足够可信的历史证据。
- 严禁：
LAST_KNOWN冒充CURRENT；严禁在只有历史快照时宣称“与基线持平”。
2. 检查失败与沙箱限制处理
- 检查脚本遇到 not found / permission denied / sandbox denied / timeout / path inaccessible 时：
- 属于
OBSERVABILITY_EVIDENCE_LIMITATION，不直接判为DEGRADED。 - 若存在历史 verified 证据：
status = <last known status>,evidence_state = LAST_KNOWN。 - 若无历史证据：
status = UNKNOWN,evidence_state = UNAVAILABLE。
- 属于
- 仅当真实规则/能力检查器本身执行并检出违规（如 capability drift > 0 或 static boundary violation）时，才标
DEGRADED。
3. Durability 契约（Backup Age 与 Repo Durability 分离）
- 明确区分 backup age 数据集（sessions, broker, configs）与 repos 数据集：
- BACKUP_RPO_AGE_BREACH：仅指 sessions/broker/configs 等备份年龄超出 RPO 目标。
- KNOWN_PRIVACY_BLOCKER / REPO_BLOCKED_PRIVACY：因包含未脱敏信息拦截推送（如 novel-main），不得被描述为“备份年龄超期”。
- REPO_UNPUSHED：存在未推送提交。
- REMOTE_UNAVAILABLE：远程仓库不可达。
- 当且仅当 sessions/broker/configs 等存在真实超期（
BACKUP_RPO_AGE_BREACH）时，才触发ACTION REQUIRED。
4. Overall Action Resolver
- ACTION REQUIRED：只有存在当前证据确认的新真实运行故障（actual Harness drift、actual backup age RPO breach、scope leakage、secret exposure、governance check failed、未预期 unpushed repo）。
- REVIEW：任一域证据不可用（
UNAVAILABLE/LAST_KNOWN）、非关键指标恶化（over-personalization）、待裁决高危提案。 - EXTERNAL BLOCKER：仅存在已知外部 blocker（
BACKUP_KEY_CUSTODY,NOVEL_REPO_DURABILITY等），且无其他新异常。 - NO ACTION：全部健康且为当前证据，无 blocker。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 125 lines · 140 tokens per session scan A d19a501fd39b
personal-ai-operations-review is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (3 stars, last pushed 6d ago), licensed MIT. It adds 140 tokens to every session and 1,681 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.