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 lunchpaillola/pipa-skills --skill pipa-keep-clientsgit clone --depth 1 https://github.com/lunchpaillola/pipa-skillsWrote 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/lunchpaillola/pipa-skills/pipa-keep-clients)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa-keep-clients"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-keep-clients/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/lunchpaillola/pipa-skills/pipa-keep-clients"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-keep-clients.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 | $0.00046 | $0.00755 |
| Opus 5 | $0.00023 | $0.00378 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
pipa-keep-clients 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 12d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipa Keep Clients
Protect trust after and around delivery.
When present, read ~/.pipa/profile.md once for durable business context. If missing, continue without blocking and do not start setup unless the user asks or a soft setup offer is useful.
Use For
- Existing-client check-ins, relationship health, retention, renewals, referrals, and testimonials.
- Follow-up wording when the user wants to keep trust or recover momentum.
- Relationship risks surfaced by delivery or closeout.
Starter Jobs
- Find who needs a check-in and why now.
- Draft or structure a follow-up. Send nothing by default.
- Surface stakeholder risk, client-health signals, renewal or retention opportunities, trust gaps, testimonials, and referrals.
- Treat generic
follow up with clientas client-retention follow-through, not reminder scheduling.
Required Inputs
- Source: client notes, stakeholder map, thread, delivery state, support signal, or
TBD. - Objective: repair, nurture, unblock, renew, ask, thank, or
TBD. - Timing, owner, and channel, if known.
Workflow
- State the relationship objective and source.
- Name the signal and why now.
- Choose the smallest useful touch: check-in, clarification, escalation, thanks, renewal prompt, or no action.
- Draft the next action when useful. Do not send.
- Capture owner, timing, source, and watchlist.
Output Contract
- Client or relationship signal.
- Why now.
- Suggested touch or ask.
- Owner and timing.
- Source/evidence or
TBD. - Watchlist items.
Boundaries
- Existing-client trust, retention, renewal, testimonial, and referral asks belong here. Acquiring a new prospect or opportunity belongs to
pipa-get-work. - Relationship follow-up with an existing client belongs here; prospect and pipeline follow-up belongs to
pipa-get-work. - Invoice and payment follow-up belongs to
pipa-get-paid, even when relationship-sensitive wording matters. - Do not send messages or schedule reminders unless explicitly asked.
- One-shot self-email reminders go through
pipa-toolstopipa-follow-up-reminders. - Active delivery status stays
pipa-deliver-workunless relationship health dominates. - Use
composio-mcponly for live email, CRM, calendar access, or an explicitly approved external send. - Route future automated client-health checks to
pipa-manageorpipa-triggers. - Do not update CRM records or access an inbox without connected-tool approval.
- Relevant connector categories include CRM, email, chat, calendar, project tracker, and knowledge base.
What ships with it
1 file 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.
- 12d ago First seen · 76 lines · 46 tokens per session scan A 7388a48bef8b
pipa-keep-clients is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 755 once invoked, about $0.0002 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
autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill…
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
compound
Capture and compound learnings from conversations into reusable commands and skills through interactive dialogue.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…