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 skills add mshadmanrahman/pm-pilot --skill briefgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/brief)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/brief"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/brief/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/mshadmanrahman/pm-pilot/brief"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/brief.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 | $0.00090 | $0.01614 |
| Opus 5.5 | $0.00036 | $0.00646 |
| Sonnet 5.5 | $0.00018 | $0.00323 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
brief 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief
One command, one decision, one reviewable artifact.
/pm-core:brief "Should we prioritize bulk import for mid-market?"
This is the first thing a new user should run. It needs no MCP servers, no configuration, and no knowledge of the other skills. It reads a folder of evidence, produces a decision brief, and forces a decision state at the end.
When to Activate
- User runs
/pm-core:briefwith or without a question - User asks "should we X", "help me decide on X", "make the case for X"
- User asks what the evidence says about a decision they are facing
- A new user has just installed PM Pilot and does not know where to start
The contract
A brief is not a summary. It is an argument with its sources attached, and it is only useful if a reader can check it. So:
- Every consequential claim names where it came from.
- Every direct quote is verified against its source before delivery.
- Evidence that cuts against the recommendation is stated, not omitted.
- Evidence that does not exist is named as missing, not inferred.
- The brief ends in a decision state, not in a draft.
If you cannot meet all five, say which one failed and why. Never deliver a brief that looks complete when it is not.
Execution
Step 1: Name the decision
Take the decision from the user's argument. If they ran the command bare, ask once:
What decision are you trying to make? One sentence, phrased as a question.
Reject a topic disguised as a decision. "Bulk import" is a topic. "Should we prioritize bulk import for mid-market this quarter?" is a decision. If the user gives a topic, offer the sharpest decision question you can infer from it and ask them to confirm or correct it in one line.
Do not proceed past a vague decision. Everything downstream inherits the framing.
Step 2: Confirm sources, once
Look for evidence in this order and show the user what you found:
- The current folder and any
evidence/,research/,interviews/,notes/,transcripts/subfolder context/product.md,context/company.md,context/personas.md,context/competitors.mdif they have content- Connected MCP tools, if any are available (Jira, Slack, Confluence, Granola, GitHub)
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 · 152 lines · 90 tokens per session scan A a61c8b0053cd
brief is a skill published in the GitHub repository mshadmanrahman/pm-pilot (22 stars, last pushed 23d ago), licensed MIT. It adds 90 tokens to every session and 1,614 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 2026-09-20.
Other skills, from other repositories
ops-standup
Cross-repo morning briefing. Aggregation of recent commits, PRs, CI, blockers and priorities of the day. Trigger when the user wants a standup, an activity summary, or to know what happened.
work-batch
Sequential execution of user stories from a PRD file. Autonomous mode that implements and commits each story one by one. Trigger when the user wants to process a backlog, execute multiple stories, or launch an autonomous mode.
notion
Search, read, create, and update Notion pages via the Notion MCP.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
create-stories
Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.
day-one-patch
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.