A task-search command for finding project tasks by words, tags, IDs, assignees, or task text. It searches the project's local task files and groups matching results by status.

For finding tasks about a topic, listing backlog items, locating tasks by tag or ID, and checking what is assigned to someone.

It removes the need to open task files one by one when looking for related work or a person's assignments.

pm-search — Skill for Claude Code by Hank95: A task-search command for finding project tasks by words…

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Hank95/mdpm

Claude Code

/plugin install 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-search.svg)](https://agentmods.dev/skills/hank95/mdpm/pm-search)

Your own site

<a href="https://agentmods.dev/skills/hank95/mdpm/pm-search"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-search.svg" alt="Measured on agentmods" 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 402 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00402
Opus 5	$0.00007	$0.00201
Sonnet 5	$0.00003	$0.00080
Haiku 4.5	$0.00001	$0.00040

Measured 5d ago against content hash 276ce179bb9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pm-search 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 5d 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-search/SKILL.md · 49 lines

What it actually says

/pm-search

Find tasks matching a query. $ARGUMENTS is the search expression.

How to run

python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" --json search "<query>" [--status S] [--tag T] [--assignee N]

Parsing the user's prompt

Extract the query and any filter hints:

"find tasks about authentication" → search "authentication"
"what's in the backlog about gallery" → search "gallery" --status backlog
"anything assigned to Danny" → search "" --assignee Danny (query can be empty — filters narrow)
"#frontend tasks" → search "" --tag frontend

Interpreting the result

Show the hits grouped by status (active first, then backlog, inbox, done, archive), with the matched field (title/tags/id/body) annotated. Keep it scannable — don't print task bodies. Example:

Found 3 matches for "gallery":

ACTIVE
  [PRJ-042] Gallery Page Component — matched in: title, tags[gallery]

BACKLOG
  [PRJ-055] Gallery analytics hooks — matched in: body

DONE
  [PRJ-001] Old gallery spec — 2026-04-10 — matched in: title

No hits → say so. Suggest broadening with --status all or dropping filters.
More than ~15 results → show the top 10 and tell the user how to narrow (tag, status, assignee).

Notes

Read-only. Never modify task files.
The CLI searches across all directories including archive/ by default. That's usually what the user wants.

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.

5d ago First seen · 49 lines · 14 tokens per session scan A 276ce179bb9a

Subscribe to this mod's changes

pm-search is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 402 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 2026-08-31.

Project Management Project management claude-code 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

coss

Helps implement coss UI components correctly. Use when building UIs with coss primitives (buttons, dialogs, selects, forms, menus, tabs, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior. Covers imports, accessibility…

usekaneo/kaneo · 80 tokens

pm-search