Borrowing it
Nothing to install: this file belongs to getappz/agentflare. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getappz/agentflare/master/.claude/skills/pm/SKILL.mdgit clone --depth 1 https://github.com/getappz/agentflareWrote 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/getappz/agentflare/pm)<a href="https://agentmods.dev/skills/getappz/agentflare/pm"><img src="https://agentmods.dev/badge/skills/getappz/agentflare/pm/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.
<a href="https://agentmods.dev/skills/getappz/agentflare/pm"><img src="https://agentmods.dev/badge/skills/getappz/agentflare/pm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00092 | $0.03973 |
| Opus 5.5 | $0.00037 | $0.01589 |
| Sonnet 5.5 | $0.00018 | $0.00795 |
| Haiku 4.5 | $0.00009 | $0.00397 |
Grade A, and why
pm 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 21d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Agent — product management over agentflare items
Two arms, one contract boundary
- Reporting (default, Part 1 below):
/pm:standup,/pm:groom,/pm:plan,/pm:health,/pm:portfolio— always read-only, never mutate. - PM mode (Part 2 below — explicit activation only: "act as project
manager", "PM mode", "e2e project management", or
/pmwith no args //pm mode on): the execution arm. Creates items, hands work off to real agents, and implements inline only small mechanical changes (Part 2, Contract rule 1). Typing the literal/pm(bare) or/pm mode on//pm mode offalso flips a session-scoped flag in agentflare's UserPromptSubmit hook (mirrors flare-code's own session-mode flag) — once set, every subsequent turn in this session gets a "PM MODE ACTIVE" reminder injected automatically, so the mode survives context compaction instead of depending on the model remembering a skill instruction. Only/pm mode offclears it; it does not expire on its own.
Never treat a reporting workflow's inputs as license to mutate, and never slip into PM mode's mutating behavior without one of the explicit triggers above.
The pm MCP tool
Every workflow in Part 1, plus mode_on/mode_off/mode_status, is also
reachable as one first-class tool call — pm (action=
standup|groom|plan|health|portfolio|mode_on|mode_off|mode_status) — instead
of composing item/project calls by hand. It's a thin wrapper (same
underlying item action=groom|standup|health / project action=list calls
this skill already teaches, just pre-shaped: groom/plan fix
state_group="backlog,unstarted", plan forces a capacity bucket,
portfolio does the per-project loop itself). Use whichever is more
convenient — a client with no skill support (not Claude Code, or PM mode's
mode_on/off without the literal /pm mode on/off prompt) has no other
way to reach this. Scoring frameworks (RICE/WSJF/...) still live in this
skill's reference/rubric.md, not in the tool — it never becomes the
caller's judgment call.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago Changed · +24 lines · +7 tokens per session 99af55d30efc
- 1mo ago Changed · +16 lines a1f613091a7c
- 2mo ago First seen · 240 lines · 85 tokens per session scan A 0d94a47e62cb
pm is a skill published in the GitHub repository getappz/agentflare (2 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 3,973 once invoked, about $0.0004 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.
Other skills, from other repositories
compliance
This skill should be used when reviewing code that handles PII, payments or health data.
ai-subscription-unit-economics
Pricing, limits, and margin gates for a product whose cost of goods is model inference — compute cost per action, cost per active user, and the breakeven limit before choosing a price, then encode the resulting caps as testable invariants. Use when pricing an AI feature or subscription tier, setting rate/usage limits…
aitask-run-gates
Run a task's declared gates — the conversational front of the headless gate orchestrator engine. Dispatches unlocked machine-gate verifiers within their retry budgets, observes human gates without self-signalling, and reports.
money
Skill "money" from Hmbown/Codewhale, covering money, when to use, setup, workflow and non-goals.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…