A command for managing a project charter, the document that defines a project's purpose, boundaries, and guiding decisions. It can create, import, find, approve, or skip that baseline.

Use it to create or import a charter, discover candidate charter files, approve the charter as a baseline, or deliberately skip it while keeping technical scanning available.

It gives the project a clear agreed reference before judging requests or making changes. It also records whether the charter came from a template, an existing file, discovery, approval, or an explicit decision to skip it.

charter — Command by wei63w

Install

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.

agentmods

npx agentmods add commands/wei63w/pm-manager/charter

Clone the repo

git clone --depth 1 https://github.com/wei63w/pm-manager

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 505 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What 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	$0.00022	$0.00505
Opus 5	$0.00011	$0.00253
Sonnet 5	$0.00004	$0.00101
Haiku 4.5	$0.00002	$0.00051

Measured 2d ago against content hash 07f5418b2574, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

charter 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.

Origin

This is a copy

100% identical to pm-charter — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/pm-manager/templates/commands/charter.md · 47 lines

What it actually says

User Input

$ARGUMENTS

Subcommands: create | import <path> | discover | approve | skip.

Outline

If $ARGUMENTS is empty, do not guess a subcommand. Show this Chinese wizard and wait:

宪章还没选定动作。请回复其一：
- create — 按模板起草宪章（仍是草稿，须再 approve）
- import <路径> — 从已有文件导入
- discover — 扫描 charter_candidates（优先 Spec Kit）
- approve — 把宪章升为基线（若 PRD 仍是草稿，同时 confirm）
- skip — 不要宪章基线；技术扫描仍可用

Then:

discover: rescan charter_candidates (Spec Kit constitution first); map into .pm/charter/; update sources.md.
import: parse given path into charter files; source=imported.
create: interactive fill from templates.
approve: charter.status=approved. If .pm/prd/prd.md is draft, also set prd.status=confirmed (same as /pm-init confirm).
skip: charter.status=absent. If the user is skipping the generated PRD, set prd.status=skipped. Do not use skipped/draft charter to judge whether a demand is “reasonable”.
Any write → needs_recompare=true.
Prefer /pm-init for first-time Spec Kit detection and PRD draft. This command is the charter lifecycle after that.
approve is the only path that makes the charter a baseline. Technical /pm-all does not require approve.

Shared Workflow (all /pm-* commands)

Read config; map-first; redact; confirm before landing generated docs.
Append audit. Closing: _closing.md 完整档（只列已有路径）。

Design baseline: docs/prd.md + 宪章。

Changes

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 · 47 lines · 22 tokens per session scan A 07f5418b2574

Subscribe to this mod's changes

charter is a command published in the GitHub repository wei63w/pm-manager (96 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 505 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to pm-charter, differing in 0 lines, and is treated as a copy.

Documents Project Management Project management agent-skills ai-agents claude-code cursor skills

charter

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

What it actually says

User Input

Outline

Shared Workflow (all /pm-* commands)

What this file has done since we first saw it

Other commands, from other repositories

webperf

spec

project

install

audit-rules

search