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 pipagit 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)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa/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"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa.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 | $0.00062 | $0.02533 |
| Opus 5 | $0.00031 | $0.01267 |
| Sonnet 5 | $0.00012 | $0.00507 |
| Haiku 4.5 | $0.00006 | $0.00253 |
Grade A, and why
pipa 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipa
Pipa routes the work around the work.
Choose one primary destination, hand off to that skill, return sources, owners, next actions, and TBD for unknowns.
Workflow
- Classify the request. Decide whether this is business work, managing Pipa, using a Pipa tool, explicit help/menu, or not a Pipa task.
- Pick one primary destination. Use the command matrix, routing rules, and tie-breakers. If no command is present, route by conversation context when safe.
- Load the destination. Prefer the standalone skill named in the matrix. Use router references only for help/menu details.
- Check route-specific gotchas. Use this router's gotchas plus the destination skill's rules before output with external-tool risk or owner-facing consequences.
- Use connectors only when needed. For setup/status, route to
pipa-manage. For live app reads/writes, keep the business lane objective, use~/.pipa/CONNECTORS.mdwhen present to resolve the preferred toolkit, then usecomposio-mcpto verify access and execute with discovery and schema checks. - Run the workflow. Preserve required inputs, approval gates, provenance, and output contract. Use
TBDfor missing facts. - Return the smallest useful next step. Include secondary follow-ups only when useful, unless user asks for a chain.
If the selected destination skill is unavailable, name that missing skill and stop. Do not imply a fallback or recreate its workflow inline.
No command? Use conversation context to choose the best destination. Show the menu only for explicit help/menu, sparse context, or unsafe routing. Not service ops, Pipa setup/config, or a Pipa utility? Do not force Pipa.
Exact Operation Routes
Explicit invocation of one of these names wins over lane aliases and adjacent operation wording:
| Entry surface | Exact operation names |
|---|---|
| Manage Pipa | pipa-setup, pipa-connectors |
| Define Work | pipa-project-charter, pipa-problem-framing, pipa-stakeholder-map, pipa-daily-plan, pipa-decision-log, pipa-requirements-brief, pipa-roadmap, pipa-scope-baseline |
| Deliver Work | pipa-work-coordination, pipa-iteration-cycle, pipa-dependency-handoff, pipa-risk-escalation, pipa-status-update, pipa-ticket-triage |
| Get Paid | pipa-change-control, pipa-budget-setup, pipa-budget-review |
| Improve Operations | pipa-acceptance-signoff, pipa-closeout-review, pipa-daily-shutdown, pipa-handover, pipa-retrospective |
What ships with it
11 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.
- evals/evals.json 28 KB
- evals/trigger-eval-set.json 3.5 KB
- references/communication-examples/budget-drift-yellow.md 636 B
- references/communication-examples/cross-functional-dependency-yellow.md 602 B
- references/communication-examples/escalation-alert-red.md 574 B
- references/communication-examples/leadership-monthly-green.md 520 B
- references/communication-examples/leadership-weekly-yellow.md 560 B
- references/communication-examples/README.md 734 B
- references/communication-examples/team-weekly-green.md 555 B
- references/communication-style.md 8.1 KB
- references/help-menu.md 2.7 KB
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 · 109 lines · 62 tokens per session scan A 9104b6fb5f3f
pipa is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 2,533 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 2026-08-31.
Other skills, from other repositories
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.
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…
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
give-me-tips
Explains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.