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-editnpx skills add Hank95/mdpm --skill pm-editgit 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-edit)<a href="https://agentmods.dev/skills/hank95/mdpm/pm-edit"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-edit.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 | $0.00018 | $0.00694 |
| Opus 5 | $0.00009 | $0.00347 |
| Sonnet 5 | $0.00004 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
pm-edit 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pm-edit
Edit frontmatter fields on an existing task. $ARGUMENTS is the ID or title fragment, optionally followed by field updates.
How to run
Delegate to the CLI — it validates values, preserves field order in the frontmatter, bumps updated, appends a work log entry summarizing the change, and renames the file if the title changed:
python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" --json edit <ref> \
[--title "New Title"] \
[--priority high|medium|low] \
[--due YYYY-MM-DD | --due null] \
[--tags a,b,c | --tags null] \
[--depends PRJ-001,PRJ-002 | --depends null] \
[--assigned-to "Name" | --assigned-to null] \
[--jira-id ENG-451 | --jira-id null] \
[--wrike-id 12345 | --wrike-id null] \
[--note "extra work log entry"]
Parsing the user's prompt
Accept natural phrasing and map to CLI flags. Examples:
- "bump PRJ-042 to high priority" →
--priority high - "change PRJ-042 due to next Friday" → resolve to ISO date →
--due 2026-04-25 - "tag PRJ-042 with auth and security" →
--tags auth,security- If the user says "also tag", read current tags via
mdpm --json show <ref>, append the new ones, pass the full list.
- If the user says "also tag", read current tags via
- "assign PRJ-042 to Danny" →
--assigned-to Danny - "clear the due date" / "remove the assignee" → pass
nullto the relevant flag - "rename PRJ-042 to 'Add MFA to login'" →
--title "Add MFA to login"(the CLI renames the file automatically)
Interpreting the result
- ok: true, changes: {...} — summarize what changed. Concise, one line per field.
- warnings: ["no fields changed"] — the user asked for a no-op. Say so and show the current values.
- ok: false, error: "validation_error" — usually a bad priority or date format. Relay the CLI message.
Immutable fields
The CLI refuses to change id, created, or status via edit. For status transitions, use /pm-start, /pm-done, /pm-block, or /pm-move.
Notes
- If the user wants to edit the task body (Objective / Acceptance Criteria / Notes), that's NOT a frontmatter edit. Use the Edit tool on the file directly — or suggest they open the task in the kanban board (
python3 board/serve.py) where the modal has an Edit button. --noteis separate from field changes. Use it when the user wants an arbitrary work-log entry alongside a metadata edit (e.g. "bump to high priority — customer escalated").
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 · 53 lines · 18 tokens per session scan A 3945f6f06323
pm-edit is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 694 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
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.
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…
verify
Build/launch/drive recipe for verifying Kaneo changes end-to-end on a local dev instance.
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…
review-checklist
Creates a local checklist for code review notes provided in the current task.
document-formatter
Formats Markdown headings, tables, and links supplied by the user.