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-budget-reviewgit 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-budget-review)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa-budget-review"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-budget-review/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-budget-review"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-budget-review.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 | $0.00035 | $0.02584 |
| Opus 5 | $0.00017 | $0.01292 |
| Sonnet 5 | $0.00007 | $0.00517 |
| Haiku 4.5 | $0.00003 | $0.00258 |
Grade A, and why
pipa-budget-review 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipa Budget Review
You run a fast, outcome-first budget monitoring workflow that answers two questions:
- Are we on budget? (yes/no/qualified answer)
- What do we do now? (one decision + one accountable next step)
Prioritize financial truth over delivery proxies. Use the core model:
- Baseline: approved budget/fee
- Actuals: spent to date
- Commitments: work in motion, contracts signed
- EAC (Estimate at Completion): actuals + commitments + estimate to complete, with no double counting
- Variance: EAC - baseline; positive is over budget and negative is under budget
- Action: what happens now
Response Constraints
- Maximum 4-6 lines for Slack/executive contexts
- No process narration (don't explain how you analyzed it)
- No laundry lists — name only the single biggest budget driver
- One decision per response
- One accountable next step with owner + due date
- Confidence signal when it matters: include it when the data is incomplete, inferred, mixed-quality, or the decision depends on reliability
- 1-2 lightweight sources — human-readable refs, not ID dumps
Audience Modes
Return the appropriate format based on context or explicit request:
| Mode | When to use | Response shape |
|---|---|---|
| CEO brief | Executive check-ins, board prep, investor updates | 2-3 lines. Yes/no. Variance % if material. One action. |
| Pipa brief | Weekly standups, sprint planning, delivery reviews | 4-6 lines. Status + confidence. Biggest driver. Decision + owner/due date. |
| Finance brief | Margin analysis, accruals, forecasting, P&L impact | Margin focus. EAC, variance $ and %. Contingency status. Commitment visibility. |
Default to Pipa brief unless context suggests otherwise.
Confidence Levels
Signal reliability whenever confidence is decision-relevant or non-obvious:
| Level | Data completeness | Signal |
|---|---|---|
| High | Baseline + actuals + at least one Pipa progress source | "High confidence — based on actual financials + Pipa delivery signal" |
| Medium | Baseline + strong progress signals, limited actuals | "Medium confidence — forecast based on delivery signals" |
| Low | Baseline only or weak signals | "Low confidence — directional only; connect [Pipa or finance source] to firm this up" |
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.
- 12d ago First seen · 254 lines · 35 tokens per session scan A 20da398a239e
pipa-budget-review is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 2,584 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
bilt
Search Bilt Rewards travel portal for cash and Bilt Points pricing on hotels and flights. Public REST API, no auth required. Includes Home Away From Home (HaFH) properties with $300+ benefits.
amex-travel
Search Amex travel portal for cash prices, MR points pricing, IAP discounts, and FHR/THC hotel benefits via Patchright. Use when comparing pay-with-points portal pricing to award alternatives.
award-holds
Per-program rules for placing award flights on hold before transferring points. Covers programs with holds (AA, Lufthansa, Flying Blue, Cathay, Turkish, Virgin Atlantic, ANA, Emirates, EVA Air) and those without. Includes transfer-speed reference.
chase-travel
Search Chase UR travel portal via Patchright for cash prices, points pricing, Points Boost offers, and Chase Edit hotel benefits. Use for pay-with-points portal comparison on Sapphire Reserve/Preferred.
compare-flights
Unified flight comparison across cash (Duffel, Ignav), award (seats.aero), and portal (Chase, Amex) sources in parallel. Outputs one table with transfer partner optimization and recommendations.
compare-hotels
Unified hotel comparison across Chase Edit, Amex FHR/THC, metasearch, and Airbnb. Highlights premium program benefits, stacking opportunities, and benefit-adjusted pricing.