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/wei63w/pm-manager/pm-docsgit clone --depth 1 https://github.com/wei63w/pm-managerWhat 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 | $0.00029 | $0.00507 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
pm-docs 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- docs — 100% identical, 0 lines differ
What it actually says
User Input
$ARGUMENTS
Accepted: empty | --draft | confirm DOC-xxx [path] | upload（用户自备）.
Outline
/pm-docs 只管文档索引与补齐。用户以中文交互时用中文回复。正式文档未经确认不得写入业务树。
- Require
.pm/。缺则建议/pm-init。 - 先读
.pm/architecture/map.json与现有.pm/state/doc-index.md（若有）。禁止为找文档做无过滤全库递归。 - 运行
pm docs（刷新索引 +.pm/state/doc-index.json）。列出缺失与possibly_stale。 - 双模式（对每条缺失）：
- 自备 / upload：告诉用户把文件放到索引
expected路径，再跑一次pm docs。 - 起草：运行
pm docs --draft，只写.pm/docs/drafts/DOC-*.md。按地图 / README / 注释填草稿，保持可编辑。停下等确认。
- 自备 / upload：告诉用户把文件放到索引
confirm DOC-xxx [path]：仅在用户明确指定正式路径后，把草稿复制过去。默认建议.pm/docs/或用户点名的docs/*.md。未指定路径则继续只留在 drafts。- 过期文档：只提示代码变更可能新于文档，默认不自动改正文。
- Closing：
_closing.md轻量档。指向doc-index.md与已有草稿。
Done When
- 索引已更新（中文）
- 草稿未写入业务树，除非用户确认了路径
- 无秘密落盘
Shared Workflow
Map-first. Redact. Confirm-before-write for official docs. Design baseline: docs/prd.md + 宪章。
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 · 41 lines · 29 tokens per session scan A 03e6e3d36f3b
pm-docs is a command published in the GitHub repository wei63w/pm-manager (96 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 507 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
spec
Start spec-driven development — write a structured specification before writing code.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
import
Import reads the legacy Agent Orchestrator flat-file store (/.agent-orchestrator) read-only and ports its projects and per-project settings into the rewrite database. Legacy files are never modified, and a re-run skips rows that already exist, so it is safe to run more than once. The daemon must be stopped before…
init
First-time setup. Auto-detects installed AI CLIs and configures targets.
commit
Create a local git commit for source skills without pushing.
completion
Generate and install shell completion scripts for tab-completion of commands, subcommands, and flags.