菜单
Use when touching Docker, CI, dependencies, runtime compatibility, or repository-level development environment instructions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | environment-maintenance |
| description | Use when touching Docker, CI, dependencies, runtime compatibility, or repository-level development environment instructions. |
Use the command packet before applying this skill's workflow:
python3 tools/agent_tools/skill_tool_commands.py show --skill environment-maintenance --format text
Execute the required and task-matching conditional commands that the packet prints.
CONTAINER_OPERATIONS.md as the source of truth for Dockerfile, docker/, .devcontainer/, validator, and Makefile target ownership. This skill is only the routing checklist.docker/packs/*.toml, docker/codex-container-profiles.toml, and docker/python-execution-rules.toml when runtime selection behavior changes.documents/server-host-contract.md and the server layout templates in the same change.agents/templates/environment_change_proposal.md when proposing a new repo-wide tool or dependency.CONTAINER_OPERATIONS.md, documents/coding-conventions-project.md, documents/github-first-module-and-devcontainer-policy.md, documents/tools/README.md, documents/server-host-contract.md, and docker/README.md.CONTAINER_OPERATIONS.md when deciding whether a tool belongs in repo-local Dockerfile / docker/ or AgentCanon-owned .devcontainer/.tools/docker_dependency_validator.sh when the boundary changes.failing_contract, observation_level,
cause_classification, intent_preservation, and evidence) before
downscoping validation or weakening an oracle.Use when agent-side working philosophy, interaction lessons, task retrospectives, repeated routing misses, missed skill invocation, or recurrence-prevention feedback should be logged without mixing them into user preferences.
Use when exploring, refactoring, or choosing an algorithm under proof obligations; builds JIT-canonical IR, lemma dependency graphs, algorithmic blocker frontiers, and algorithm-change guidance before handing terminal proof work to formal-proof-workflow.
Use when designing, implementing, reviewing, or diagnosing numerical optimization, solvers, preconditioners, convergence, gradients, Jacobians, Hessians, KKT conditions, tolerances, or optimization benchmarks; fixes the mathematical and validation contract before code or experiment changes.
Use when a change needs oracle/spec-risk classification or resilient, adversarial static test design, including behavior contracts, oracle choice, property/metamorphic candidates, mutation adequacy, or brittle-test diagnosis.
Use when updating AgentCanon itself, refreshing a vendored vendor/agent-canon submodule pin, repairing AgentCanon root runtime views, applying AgentCanon update TODOs, or routing local AgentCanon source commits through a proper AgentCanon branch and PR before parent pin updates.
Use when accumulated AgentCanon eval evidence is missing, stale, or failing; runs registered eval producers, validates eval family accumulation, and stores evidence through the log archive instead of hand-writing reports.