A guided command for reviewing untriaged requests in a task inbox. Triage means deciding whether each incoming item should be accepted, started, planned, rejected, postponed, or assigned.

For reviewing new requests, setting their priority and tags, moving them into active or backlog work, planning larger items, or postponing them.

It turns an unorganised list of incoming requests into deliberate project decisions, one item at a time.

pm-inbox — Skill for Claude Code by Hank95/mdpm

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.

Any agent

npx skills add Hank95/mdpm --skill pm-inbox

Clone the repo

git clone --depth 1 https://github.com/Hank95/mdpm

Made for: Claude Code.

Or install mdpm, the plugin that ships this one along with the rest of its 17 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hank95/mdpm/pm-inbox/github.svg)](https://agentmods.dev/skills/hank95/mdpm/pm-inbox)

Your own site

<a href="https://agentmods.dev/skills/hank95/mdpm/pm-inbox"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-inbox/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hank95/mdpm/pm-inbox"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 752 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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 5.1	$0.00014	$0.00752
Opus 5.5	$0.00006	$0.00301
Sonnet 5.5	$0.00003	$0.00150
Haiku 4.5	$0.00001	$0.00075

Measured 1mo ago against content hash 6a71df604243, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm-inbox 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 1mo 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.

skills/pm-inbox/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pm-inbox

Walk through tasks/inbox/ one item at a time and decide what to do with each.

Steps

List inbox contents.
- If tasks/inbox/ is empty or missing, say so and exit. Optionally, offer to pull new items from Jira/Wrike via /pm-sync-jira or /pm-sync-wrike.
Sort inbox by created date ascending (oldest first — stop things from rotting).

For each item, show this summary to the user:

## Inbox item 1 of N: [PRJ-INBOX-003] Short title
Source: <from jira_id or wrike_id if present, else "direct">
Created: YYYY-MM-DD

<Objective section, truncated to ~3 lines>

**Triage options:**
a) Accept → move to backlog (set priority, tags, due)
b) Start now → move directly to active
c) Plan → run /pm-plan to decompose
d) Reject → delete (or archive if synced to Jira/Wrike)
e) Snooze → leave in inbox, move on
f) Delegate → set assigned_to and leave in backlog

Process the user's choice:
- Accept: Ask for priority (default medium), tags, optional due date. Update frontmatter. Assign a real task ID (replace any PRJ-INBOX-* placeholder with the next sequential PRJ-XXX). Rename the file to <new-id>-<slug>.md to match the MDPM filename convention. Move to tasks/backlog/.
- Start now: Same as Accept (including the filename rename), but move to tasks/active/ and set status: active. Append work log entry: "Triaged from inbox, started work."
- Plan: Keep the inbox file in place, invoke /pm-plan logic on its contents. After planning, move the original inbox item to done/ with a work log entry "Replaced by decomposition into PRJ-XXX, PRJ-YYY."
- Reject: Confirm with the user. If the task has a jira_id or wrike_id, offer to close it in the external system via sync. Then delete the file (inbox is the ONLY directory where deletion is allowed).
- Snooze: No change. Move to next item.
- Delegate: Ask for assignee name, set assigned_to, move to tasks/backlog/.

Read the full file on GitHub · 58 lines

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.

1mo ago First seen · 58 lines · 14 tokens per session scan A 6a71df604243

Subscribe to this mod's changes

pm-inbox is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 752 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Project Management Project management claude-code-plugin jira kanban markdown

project-manager

This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.

buiphucminhtam/forgewright · 68 tokens

submission

This skill should be used when the user asks to "write a query letter", "query", "querying", "pitch", "blurb", "back cover copy", "jacket copy", "comp titles", "comparable titles", "synopsis for agents", "submit to agents", "submission tracker", "self-publishing description", "retailer description", "ready to query"…

danjdewhurst/story-skills · 201 tokens

kaneo-cli

Work with Kaneo tasks, projects, comments and time tracking through the kaneo CLI. Use when the user asks to list, create, update, assign or close Kaneo tasks, see what is assigned to them, comment, log time, or script against a Kaneo workspace on Kaneo Cloud or a self-hosted instance.

usekaneo/kaneo · 73 tokens

alive:create-walnut

Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.

alivecontext/alive · 63 tokens

alive:bundle

Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.

alivecontext/alive · 34 tokens

stale-ticket-triage

Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.

aozyildirim/Agena · 57 tokens