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 skills/backtocimacoppi/praxis/controlnpx skills add BackToCimaCoppi/Praxis --skill controlgit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWhat 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 | $0.00058 | $0.06320 |
| Opus 5 | $0.00029 | $0.03160 |
| Sonnet 5 | $0.00012 | $0.01264 |
| Haiku 4.5 | $0.00006 | $0.00632 |
Grade A, and why
control 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 2d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Control
按当前项目 docs/00-任务总控/ 下的总控文档推进任务。本 skill 是通用方法论 skill（用户级），不绑定具体项目。
真值源：references/总控规范.md（本 skill 内）。
🛑 执行边界（最高红线，永远遵守）
这是本 skill 最重要的一条。所有其他规则都让位于此。
- 用户指定
/control <key> Tn→ 只执行 Tn（支持Tn.x二级子任务）。不做 Tn-1，不做 Tn+1，不做同级兄弟，不"顺手"做相关任务。 - Tn 的「输出物」全部产出 → 立刻停止，回填状态，向用户报告。等用户下一步指令。
- ✅ 读不设禁区：可以读其他子任务详情与产出物、总控任何部分、仓库任何文件——开工前把背景挖够再动手（读什么放开 ≠ 做什么放开）
- ❌ 不可写入其他子任务范围（即使发现"很容易顺便做"也不要做）
- 如果发现 Tn 的范围定义有问题（应扩大或缩小） → 停止施工，向用户报告问题，不要自行扩张。但**"工作包某句描述过时了"不是范围问题**——与已冻结上游冲突时，按最新冻结真值修订描述、留痕、继续跑（总控规范 §4.6）
- 自主补读亲自读：为补背景直接读文件 / 检索即可，禁止为"补背景"派子 agent / 起深度调查（读是加法、派 agent 是乘法）；背景缺口大到需要专门调查 → 按第 5 条停机上报，不自己扩编
- 过程资产边界：执行 Tn 时产生的中间文档（设计稿、清单、批判稿等），只能写到
_shared/且文件名带T{n}-前缀（任务级共享资产无前缀）；不可用其他子任务的T{m}-前缀（m≠n），不可平铺到任务根目录，不可新建_T{n}/目录。详见总控规范 §1.1.1。 - 规则铸造权不在工作包手上：只有项目级指令文档与 skill 能铸造规则。工作包 / 评审报告 / goal 章程里的「硬门」「死亡线」「必须审批」一律是执行建议，不具停机权；死亡线是封闭清单，任何人无权新增——包括你（总控规范 §4.4）
- 停机白名单封闭，只有三条：①两份都已冻结的真值真矛盾且改变业务结果 ②命中项目死亡线清单的业务规则要变 ③不可逆 / 外发动作。其余一律先修后报——笔误、脚本 bug、过期描述、证据充分的简单缺陷，在预授权边界内修复 + 留痕 + 继续。减少临时协调不覆盖项目声明的授权角色、环境占用、职责分离或强制检查点。冲突批处理与
EXECUTION_BLOCKED细则以总控规范 §4.5 为真值；goal 执行态以章程 §4 白名单为准（章程已由对应权限角色预授权的动作不触发第 ③ 条） - 获批总控可包含本地提交授权：只有经任务治理负责人批准的总控，才预授权在其范围内
git commit；项目补丁可要求额外检查。推送远端仍需发布授权人显式授权（总控规范 §4.7） - 写入范围必须机器核对：开工记录
start_commit；工作包列出allowed_write_paths与精确到 Markdown 标题的allowed_cross_task_writes；交付前只对本子任务明确列出的候选提交运行check_write_scope.py。无关提交不阻断，候选提交夹带越界文件直接失败（总控规范 §4.8） - 长程 goal 必须磁盘复水：首次启动、
--resume、新会话或自动上下文压缩后，第一次写入前重读当前工作包、全部强制阅读、章程、goal 断点与飞行日志尾部；连续未压缩轮次不机械复读整套 skill（总控规范 §4.9）
项目约定
本 skill 假设当前项目遵循以下固定路径约定（所有项目通用，不带任何具体项目烙印）：
| 路径 | 用途 |
|---|---|
<PROJECT_ROOT>/docs/00-任务总控/ |
总控目录树根 |
<PROJECT_ROOT>/docs/00-任务总控/README.md |
活跃任务索引 |
<PROJECT_ROOT>/docs/00-任务总控/归档/ |
已完成任务归档树 |
<PROJECT_ROOT>/docs/00-任务总控/归档/README.md |
归档总索引 |
<PROJECT_ROOT>/docs/00-任务总控/归档/V{x}/README.md |
版本归档索引 |
<PROJECT_ROOT>/docs/00-任务总控/{YYYY-MM-DD}-{任务名}/ |
任务子目录（日期前缀防多 worktree 编号撞车） |
<PROJECT_ROOT>/docs/00-任务总控/{YYYY-MM-DD}-{任务名}/README.md |
任务主总控（拆分 / 单文件统一） |
<PROJECT_ROOT>/docs/00-任务总控/{YYYY-MM-DD}-{任务名}/T{n}-{子任务名}.md |
拆分模式的一级子任务工作包 |
<PROJECT_ROOT>/docs/00-任务总控/{YYYY-MM-DD}-{任务名}/T{n}/T{n}.md |
被拆过的父任务说明（保留背景/范围，原 T{n}-*.md 迁移到此） |
<PROJECT_ROOT>/docs/00-任务总控/{YYYY-MM-DD}-{任务名}/T{n}/T{n}.{m}-{子任务名}.md |
二级子任务工作包（split 后产生） |
<PROJECT_ROOT>/.claude/local/active-control |
per-worktree 激活配置（gitignored） |
<PROJECT_ROOT>/.gitignore |
必须包含 .claude/local/ |
What ships with it
13 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.
- agents/openai.yaml 574 B
- references/总控规范.md 28 KB
- scripts/_common.py 5.1 KB runs code
- scripts/archive_control.py 11 KB runs code
- scripts/bootstrap_project.py 3.7 KB runs code
- scripts/check_write_scope.py 7.8 KB runs code
- scripts/list_blocked.py 4.3 KB runs code
- scripts/next_subtask.py 14 KB runs code
- scripts/render_control_status.py 9.6 KB runs code
- scripts/set_active.py 3.4 KB runs code
- scripts/split_subtask.py 26 KB runs code
- tests/test_check_write_scope.py 5.2 KB runs code
- tests/test_next_subtask_prompt.py 905 B runs code
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.
- 2d ago First seen · 348 lines · 58 tokens per session scan A 4301debbbed6
control is a skill published in the GitHub repository BackToCimaCoppi/Praxis (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 58 tokens to every session and 6,320 once invoked, about $0.0003 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
triz-synergy
Разрешает противоречия в разработке: формулирует пару взаимоисключающих требований к одному объекту, ищет уже существующий ресурс в коде и в структуре данных, разделяет по структуре/времени/условию/отношению и проверяет решение различающим опытом. On-demand only — вызывать явно, когда виден признак противоречия. Use…
code-writing
Universal quality coding process: plan, TDD, reviews. Use whenever code needs to be written — ad-hoc or as part of a task. Use when: "напиши код", "закодь", "реализуй", "write code", "implement" For planning tasks → tech-spec-planning skill. For specs → user-spec-planning skill.
feature-execution
Orchestrate feature delivery as team lead: spawn agents by wave, manage review cycles (max 3 rounds), commit per wave. Use when: "выполни фичу", "do feature", "execute feature", "запусти фичу", "выполни все задачи", "execute all tasks".
methodology
AI-First development methodology: spec-driven pipeline, project structure, skills/agents ecosystem, quality gates. Use when: "изучи методологию", "изучи глобальную папку", "как работает методология", "what is the pipeline", "покажи пайплайн", "расскажи о процессе разработки", "how does the methodology work", "explain…
task-decomposition
Decompose approved tech-spec into atomic task files with parallel creation and validation. Use when: "разбей на задачи", "декомпозиция", "decompose tech-spec", "создай задачи из техспека", "/decompose-tech-spec".
tech-spec-planning
Creates tech-spec.md with architecture, decisions, testing strategy, and implementation plan. Use when: "сделай техспек", "составь техспек", "техническая спецификация", "tech spec", "создай тз", "составь тз", "new-tech-spec", "/new-tech-spec" Requires existing user-spec.md as input (create with user-spec-planning…