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/snakeying/textum/prd-plangit clone --depth 1 https://github.com/snakeying/TextumWhat 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 | $0.00000 | $0.01114 |
| Opus 5 | $0.00000 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
prd-plan 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段1a: 需求澄清(写入 YAML plan-pack)
读取:docs/prd-plan-pack.yaml(如存在) | 写入:docs/prd-plan-pack.yaml(每轮更新;纯 YAML;不包含 ```) | 模板:.claude/textum/prd-plan-pack-template.yaml
目标:把已确认事实持续写入 docs/prd-plan-pack.yaml(唯一事实来源),直到满足 READY 门禁。
输出规则(必须遵守)
输出必须二选一(除此之外不要输出任何解释/复述):
IN_PROGRESS:- 只输出两块内容:
- 本轮问题(≤4;只问 blockers)或 本轮变更摘要(YAML 路径列表)
- 剩余 blockers(≤8;按优先级)
- 只输出两块内容:
READY:- 只输出三行纯文本:
READY已写入:docs/prd-plan-pack.yaml下一步:/prd
- 只输出三行纯文本:
- 不输出 YAML 正文(包括
docs/prd-plan-pack.yaml与PRD_PLAN_CLARIFY_PACK)
写入规则(必须遵守)
- 未确认信息不得写入;未知保持为空/空数组
- 仅当用户明确说“无/不适用/没有”时才写
N/A或None - 不改写用户给出的 token(尤其
modules[].feature_points[].landing)
PRD_PLAN_CLARIFY_PACK 处理(必须)
当用户粘贴 PRD_PLAN_CLARIFY_PACK 时:
- 只围绕
blockers提问(≤4) - 收集答案后,按
blockers[].path回填到docs/prd-plan-pack.yaml(保留其它已确认字段) - 输出「本轮变更摘要(路径列表)」+「剩余 blockers」
READY 门禁(必填路径清单)
project.name、project.one_liner非空goals[0+]、non_goals[0+]:每条非空scope.in[0+]、scope.out[0+]:每条非空roles[0+]:每个 role 的role/description非空;typical_scenarios[0+]且每条非空permission_matrix.operations[0+]:每行op非空;per_role至少 1 个 key(key 必须是roles[].role子集;value 只能是A/D/O);note可为N/Amodules[0+]:每个模块id/name/summary/priority非空;且至少 1 个模块priority = P0modules[].feature_points[0+]:每条fp/desc/landing非空(landing允许N/A)modules[].scenarios[0+]:每条actor/given/when/then非空(fail_or_edge/note可为N/A)business_rules[0+]:每条id/desc/scope非空(exception_or_note可为N/A)- 稳定 ID:
modules[].id必须唯一且符合M-01格式modules[].feature_points[].fp必须全局唯一且符合FP-001格式business_rules[].id必须唯一且符合BR-001格式
api.has_api必须为布尔值:false:api.endpoints=[];api.base_url/auth/...可为N/Atrue:api.base_url非空且不为N/A;api.auth非空且不为N/A(无认证写None);api.endpoints[0+]且每条method/path/permission/summary非空
modules[].feature_points[].landing合法性(不改写 token):- 允许:
N/A或逗号分隔多项集合 - 每项必须以
DB:/FILE:/CFG:/EXT:之一开头 - 若出现
DB:<table>:该<table>必须能在data_model.tables[].table中找到
- 允许:
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.
- 3d ago First seen · 69 lines · 0 tokens per session scan A bbb26774f420
prd-plan is a command published in the GitHub repository snakeying/Textum (41 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,114 tokens. 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
ask
数学研究操作系统入口:自动诊断用户意图,路由到思想透镜、数学知识库或设计翻译层。 English: Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
ask
Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.