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/kv0906/pm-kit/previewnpx skills add kv0906/pm-kit --skill previewgit clone --depth 1 https://github.com/kv0906/pm-kitWhat 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 | $0.00061 | $0.01225 |
| Opus 5 | $0.00030 | $0.00613 |
| Sonnet 5 | $0.00012 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
preview 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 2d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/preview — HTML Preview
Render vault content as styled HTML for browser viewing. Markdown stays the source of truth; HTML is the presentation layer.
Context
Today's date: !date +%Y-%m-%d
Config: @_core/config.yaml Preview rules: @.claude/rules/preview-formats.md HTML shells: @_templates/html/ Processing logic: @_core/PROCESSING.md
Usage
/preview docs/project-a/checkout-flow.md
/preview decisions/project-a/2026-06-29-auth-approach.md
/preview progress all
/preview progress project-a --week
/preview decide auth-approach
/preview block api-rate-limit
/preview meet 2026-06-29-sync-sprint-review
/preview reports/2026-06-29-progress-all.md
Flags
| Flag | Effect |
|---|---|
--with-links |
Inline first paragraph from linked notes |
--no-open |
Write HTML only, do not open browser |
--shell memo|prd|status|executive |
Force template shell |
--link |
Write preview: path to source note frontmatter |
Session Task Progress
TaskCreate: "Resolve preview source"
activeForm: "Resolving preview source..."
TaskCreate: "Render HTML"
activeForm: "Rendering HTML preview..."
TaskCreate: "Open and verify"
activeForm: "Opening preview in browser..."
Processing Steps
1. Parse Input
Determine source mode:
| Input pattern | Action |
|---|---|
Path to .md file |
Read that file directly |
progress {project|all} |
Synthesize like /progress, use status shell |
decide {slug} |
Glob decisions/*/*{slug}*.md, pick latest |
block {slug} |
Glob blockers/*/*{slug}*.md |
meet {slug} |
Glob meetings/*{slug}*.md |
doc {project} {slug} |
Read docs/{project}/{slug}.md |
If ambiguous, ask user to clarify path.
2. Gather Content
File mode: Read markdown + frontmatter.
Synthesis mode (progress): Follow /progress gather steps:
- Scan dailies, blockers, docs, decisions for project/timeframe
- Build structured sections: Shipped, In Progress, Blockers, Decisions
- Count metrics for status shell
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.
- 2d ago First seen · 160 lines · 61 tokens per session scan A 58bba33be61d
preview is a skill published in the GitHub repository kv0906/pm-kit (133 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,225 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
critique-agent
Pressure-test an existing product brief or PRD pack — find gaps, hidden assumptions, inconsistencies, and failure modes before stakeholder review. Use when: critique brief, critique PRD, devils advocate, red team, pressure test, find holes, what could go wrong, stress test the doc, pre-mortem.
interview-frameworks
Frameworks for user interviews, question design, and qualitative research. Use when conducting user interviews, designing interview guides, researching user needs, or gathering qualitative insights. Trigger on: 'create an interview guide', 'how do I interview users', 'customer discovery questions', 'user research…
query-datasets
Answer grounded yes/no questions about what exists in the 03-datasets/ example corpora (supporttickets, calltranscripts) using the local SQLite + FTS5 + vector hybrid index. Use when the user asks 'do/does [corpus] contain/mention/include/have requests for X?', 'any [corpus] about Y?', or similar factual queries over…
critique-prd
Rubric-score a PRD pack (02 + 03) against the 7-dimension PM Brain rubric and run a 4-persona panel review. Returns scores, panel critiques, the single weakest section, a concrete rewrite, and P0/P1 fix lists. Use when: PRD review, score my PRD, rubric review, panel review, rewrite weakest section, critique-prd.
create-prd
Write the PRD pack (02-product-requirements.md + 03-success-metrics.md) on top of an approved product brief. Use when: PRD, product requirements, requirements doc, success metrics, spec writeup, shape the PRD.
create-internal-feature-announcement
Drafts an internal feature announcement (IFA) from the PRD pack and user sources using the repo template, then writes 04-internal-feature-announcement.md. Use when: IFA, internal feature announcement, internal FAQ, Slack IFA prep, launch comms pack, or internal product documentation from the template.