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 commands/awardtravelfinder/mcp/compare-programsgit clone --depth 1 https://github.com/AwardTravelFinder/mcpWrote 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/commands/awardtravelfinder/mcp/compare-programs)<a href="https://agentmods.dev/commands/awardtravelfinder/mcp/compare-programs"><img src="https://agentmods.dev/badge/commands/awardtravelfinder/mcp/compare-programs.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.00401 |
| Opus 5 | $0.00003 | $0.00200 |
| Sonnet 5 | $0.00001 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
compare-programs 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 5d 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.
What it actually says
Compare Loyalty Programs
The user wants to compare loyalty program award charts across the 23 programs Award Travel Finder supports.
Arguments
The user invoked this command with: $ARGUMENTS
Parse arguments for program names or slugs. If none provided, suggest the most common comparisons (Avios vs Aeroplan, Flying Blue vs Virgin, etc.) and ask which to compare.
Available program slugs:
british-airways, iberia, qatar-airways, aer-lingus, virgin-atlantic, aeroplan, flying-blue, cathay-pacific, singapore-airlines, emirates, etihad, turkish-airlines, ana, jetblue
Process
- Use
get_program_ratesfor each requested program. - If a specific route is mentioned, also run
get_pricingto anchor the comparison to real numbers for that route. - If a region is mentioned, filter results to that area.
- Present a comparison table: Destination/Region | Cabin | Program A points + taxes | Program B points + taxes
- Highlight which program offers the best value for each cabin class.
- Note off-peak vs peak pricing differences and fuel surcharge gotchas (BA and Virgin tend high; Aeroplan, Asia Miles, Flying Blue tend lower or zero on partner metal).
Examples
/atf:compare-programs british-airways emirates
/atf:compare-programs aeroplan flying-blue virgin-atlantic
/atf:compare-programs cathay-pacific ana for HKG-NRT
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.
- 5d ago First seen · 38 lines · 7 tokens per session scan A 4e0a01cc05f6
compare-programs is a command published in the GitHub repository AwardTravelFinder/mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 7 tokens to every session and 401 once invoked, about $0.0000 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 commands, from other repositories
audit
Audit a Japanese construction or renovation quote against JCCDB fair-price data.
verify
Issue an independently verifiable, tamper-evident fair-price receipt.
tenders
Procurement market intelligence — award-value benchmarks, top suppliers, incumbency and concentration, from the UK Tenders MCP.
finops
Create FinOps strategy with cloud cost management, optimization, governance, and forecasting.
sobc
Create Strategic Outline Business Case (SOBC) using UK Government Green Book 5-case model.
checklist
Generate a custom checklist for the current feature based on user requirements.