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/wei63w/pm-manager/pm-exportnpx skills add wei63w/pm-manager --skill pm-exportgit 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 | $0.00016 | $0.00575 |
| Opus 5 | $0.00008 | $0.00287 |
| Sonnet 5 | $0.00003 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
pm-export 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
- Prefer
pm exportfrom the project root (--from/--to/--out，可选--with-diagrams)。Default output:.pm/exports/pm-export-YYYYMMDD.md。 - The file must include: audit window, dialogue notes, snapshot excerpt, reviews table, test-gaps, guard, and architecture paths (embed
.mmdonly with--with-diagrams). If the CLI is unavailable, assemble the same sections and redact before writing. If residue remains (AKIA…,BEGIN PRIVATE KEY), delete the file and fail. - Exclude
local.yaml, credentials, raw logs, secret originals. Never include un-redacted secrets. - Show the export path and ask the user to open it.
Shared Workflow (all /pm-* commands)
Follow this order when the command mutates .pm/ state:
- Read
.pm/config/project.yamland.pm/config/local.yaml(if missing and command is not init → recommend/pm-init). - If
.pm/metadata is valid, load it; do not force a full-repo rescan. On-demand incremental scan usingsources+extra_scan_roots+--path+ conversation paste (highest priority for/pm-fix). Prefer.pm/architecture/map.jsonand the document index before walking the tree. - Desensitize evidence →
.pm/evidence/scans/{command}-{timestamp}.json(secrets →***). Never persist raw secrets. - Optional charter compare only when
charter.status == approved(attachconfidence). Draft PRD/charter MUST NOT be used as the baseline. - Incremental merge into module
findings.md/todo.md; sync authoritativestate/todo.md. - Refresh
state/overview.mdwith all open/in_progress blocking+high todos (no 3-item cap). Medium/low: counts only unless--verbose. - Append audit to
.pm/state/audit.jsonl(command, time, input/output summary; include reasoning when the step was AI-produced). - Output risk summary + recommended next step (≤20 lines). Never auto-write source/SQL/cloud or land generated docs/rules without explicit user confirmation.
- Closing:
_closing.md完整档（只列已写出的导出文件）。
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 · 35 lines · 16 tokens per session scan A 1b6ef67962f4
pm-export is a skill published in the GitHub repository wei63w/pm-manager (96 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 575 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 skills, from other repositories
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a…
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
verification-before-completion
在宣称工作完成、已修复或测试通过之前使用，在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功；始终用证据支撑断言.