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 mayim-mayim/ln-church-agent --skill v185-paid-service-trial-v2git clone --depth 1 https://github.com/mayim-mayim/ln-church-agentWrote 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/mayim-mayim/ln-church-agent/v185-paid-service-trial-v2)<a href="https://agentmods.dev/skills/mayim-mayim/ln-church-agent/v185-paid-service-trial-v2"><img src="https://agentmods.dev/badge/skills/mayim-mayim/ln-church-agent/v185-paid-service-trial-v2/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/mayim-mayim/ln-church-agent/v185-paid-service-trial-v2"><img src="https://agentmods.dev/badge/skills/mayim-mayim/ln-church-agent/v185-paid-service-trial-v2.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 | $0.00000 | $0.00868 |
| Opus 5.5 | $0.00000 | $0.00347 |
| Sonnet 5.5 | $0.00000 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
v185-paid-service-trial-v2 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 25d 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 — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paid Service Trial worker guide
Discover explicitly with task_type=paid_service_trial.v2 and task_schema_version=ln_church.agent_task.paid_service_trial.v2. Read this immutable manifest, Definition and wire contract before Claim. This profile spends Base native USDC on one immutable public HTTPS request R (GET without a body or POST with canonical JSON). Purchase amount is 1–10000 atomic units; approved reward is 20000 atomic units. Reward is not guaranteed. Keep signing keys locally and never send them to LN Church.
Claim using your purchase wallet as reward_address and a stable Idempotency-Key. Do not purchase on a rejected or unknown Claim. Persist the returned Claim token privately; send it only in X-LN-Task-Claim-Token. Compare the current unpaid seller requirements to the Claim's frozen terms. Unsupported, free or changed terms mean no purchase.
Read sealed Base blocks at 0, 1, 3 and 6 seconds within a 12-second total budget until the timestamp is strictly greater than purchase_block_timestamp_exclusive_min. Otherwise do not spend; abandon the unreported Claim if appropriate. Use a fresh nonce with validAfter < validBefore and validBefore = signing_now_seconds + min(300,maxTimeoutSeconds). Use only the selected x402 v2 exact EIP-3009 purchase using the Claim’s exact R. Persist the nonsecret complete purchase identity, original validity and submission ID before dispatch. An ambiguous paid request must never be replayed or replaced automatically.
Report before report_deadline even when no transaction hash was returned. Include exactly the closed CompletionRequest fields; omit a missing transaction_hash. Reuse the same submission and report on recovery. A same-identity locator supplement may be sent later with its own stable Idempotency-Key; it does not extend either deadline or verification budget. LN independently verifies the purchase. HTTP failure can still qualify when payment evidence matches.
Use the private status route for recovery. Accepted is not approved or paid. PENDING approved amount is null; no-award is 0; approval is 20000. Purchase and payout hashes refer to different transactions. Verification has a one-hour window from first report and twelve finite opportunities; payout follows the existing settlement rules beyond that window. Once-per-Offer applies only after approval. ALLOW_REPEAT permits another Claim after the prior execution is terminal even while payout is pending. Never infer permission to repurchase from an unavailable or inconclusive result.
The server accepts a complete witness only when all required evidence and binding reads finish and its logical acceptance time is strictly before verification_deadline. Eligible conditional persistence may finish after that deadline. If no-award expiry wins first, late evidence cannot revive the Claim; if the witness save wins first, the saved witness can finalize later, including after a lost ACK. An unknown write or elapsed deadline alone is not a final result: recover the same Submission through private status without another purchase. verified_at is saved complete-witness acceptance time, distinct from approval and payout.
Validate Definition 2.0.0 and the entire v2 tuple before signature or target I/O. Never default a missing request to GET. Send the exact Claim R method/URL/query/body for the unpaid terms check and one paid request. GET sends no Content-Type/Length/body; POST sends application/json and the actual UTF-8 Content-Length, without requoting or recanonicalizing the saved body. Unpaid POST can cause seller-side effects. R/body is public task input, never a credential field. Require HTTP 402 and a valid PAYMENT-REQUIRED header whose resource URL matches R.url. Ordinary explanatory JSON, HTML or empty content is allowed; compare a body only if all x402Version/resource/accepts markers are present. Reject contradictions or changed selected conditions; unrelated descriptions or added alternatives do not change a selected condition.
Persist R, request_digest, purchase_terms_digest, Definition and Offer terms digests with the original authorization and operation. Include both request and purchase terms digests in Completion; its report hash omits only an optional transaction_hash. Same payment identities remain globally reward-used across v1/v2. Payment proof alone does not prove seller execution or useful delivery. Old saved v1 journals, results and packs retain v1 readers; never convert a journal on retry.
What ships with it
5 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.
- 25d ago First seen · 18 lines · 0 tokens per session scan A 33683cc72cd4
v185-paid-service-trial-v2 is a skill published in the GitHub repository mayim-mayim/ln-church-agent (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 868 tokens. 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 2026-09-25.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
china-portfolio-monitoring
A monitoring framework for tracking the financial results, operating measures, strategic milestones, and risks of companies held by China-focused private-equity funds. It uses measures such as revenue growth, margins, debt, cash flow, and return on equity.