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/hank95/mdpm/pm-blocknpx skills add Hank95/mdpm --skill pm-blockgit clone --depth 1 https://github.com/Hank95/mdpmWrote 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.
[](https://agentmods.dev/skills/hank95/mdpm/pm-block)<a href="https://agentmods.dev/skills/hank95/mdpm/pm-block"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-block.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00013 | $0.00526 |
| Opus 5 | $0.00006 | $0.00263 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
pm-block scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/pm-block
Mark a task blocked when progress is stopped by something external — a review, a missing decision, an API that's down, another team's work.
Blocked vs waiting: don't confuse them. "Waiting" means depends_on points at a task that hasn't shipped yet — that's just sequenced work. "Blocked" means someone outside the task's normal path has to act before it can move.
How to run
Delegate to the CLI — it sets status: blocked, bumps updated, and appends the reason to the Work Log atomically:
python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" --json block <ref> <reason...>
Example:
python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" --json block PRJ-042 waiting on security review from Alice
Parsing the user's prompt
- Strip the task ID / ref from
$ARGUMENTS— first token. - Everything after is the reason. Pass it as positional args.
- If no reason is given, ask — don't call the CLI.
mdpm blockrejects empty reasons with a validation error anyway. A block without context rots in/pm-status.
Interpreting the result
- ok: true — confirm with a short summary. Tell the user the block will show up in
/pm-statusunder Blockers until cleared with/pm-edit PRJ-042 status=activeor the blocker command chain below. - ok: false, error: "precondition_failed" — can't block a task that's in
done/orarchive/. Suggest/pm-newfor a follow-up.
External sync
If the task has a jira_id or wrike_id, offer to push the block state as a comment to the external system via /pm-sync-jira or /pm-sync-wrike.
Unblocking
To clear the block, use /pm-unblock <ref> — it restores status: to the directory-derived value and logs "Unblocked." in the work log.
Notes
- A blocked task stays in its current directory (usually
active/). Moving it to a "blocked" directory would hide it from the active queue — we want it visible so it doesn't get forgotten. - The CLI's reason is mandatory. Never fabricate one.
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 · 48 lines · 13 tokens per session scan A 2ddea3aa2025
pm-block is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 526 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.
Other skills, from other repositories
sideboard
Maintain and display a live project roadmap/kanban board backed by GitHub Issues. Use when the user asks to see, set up, or update the roadmap, add a feature to build next, mark an item in-progress or done, or when a chat naturally decides on upcoming work worth tracking. Manages the roadmap via gh (GitHub Issues) and…
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.
kanban-md
Manage project tasks using kanban-md, a file-based kanban board CLI. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or…
kanban-based-development
Autonomous, parallel-safe development workflow using kanban-md. Use when the user asks to work through tasks, do kanban-based development, or when multiple agents need to coordinate work on the same codebase. Optimized for explicit handoffs and a "defer to user" protocol when human intervention is required.
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.
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.