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 zkp2p/zkp2p-skills --skill peer-protocol-tracegit clone --depth 1 https://github.com/zkp2p/zkp2p-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/zkp2p/zkp2p-skills/peer-protocol-trace)<a href="https://agentmods.dev/skills/zkp2p/zkp2p-skills/peer-protocol-trace"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-protocol-trace/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/zkp2p/zkp2p-skills/peer-protocol-trace"><img src="https://agentmods.dev/badge/skills/zkp2p/zkp2p-skills/peer-protocol-trace.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 | $0.00036 | $0.01005 |
| Opus 5.5 | $0.00014 | $0.00402 |
| Sonnet 5.5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
peer-protocol-trace 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 9d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Peer intents, deposits, and transactions
Use this for one concrete incident or a bounded set of related deposits/intents. Establish the chain/environment and supplied identifier first. A transaction hash, intent hash, and composite deposit ID are different keys; a numeric deposit ID needs its escrow address. Do not infer identity by searching unrelated wallets.
Reconstruct the lifecycle
Use @zkp2p/[email protected] for protocol/indexer reads and @zkp2p/[email protected] for current entity types. The checked example uses the supported indexer wrappers. Configure a read-only wallet address, chain/RPC, and runtime environment; indexer credentials, if needed, remain in the host's secret store. Do not use a retired HyperIndex URL from another environment.
- If given a transaction, fetch it and its receipt from that chain. Record status, block, sender, destination contract, and decoded relevant events using the matching deployed ABI. A transaction being found or mined is not enough: check receipt success. If pending/unknown, say so before treating missing events as absence.
- Look up an intent with
client.indexer.getIntentByHash(hash)or deposit withgetDepositById(id, { includeIntents: true }). For an owner-scoped question use a boundedgetOwnerIntents/deposit query. Preserve full IDs returned by the indexer rather than rebuilding them from obsolete SDK comments. - Follow intent → escrow/deposit → owner/recipient → signal, fulfillment, cancellation/prune, and extension events. Read the actual on-chain intent via
client.getIntentwhere applicable; it can be absent after settlement/pruning, so a missing active record does not erase receipt history. - Reconcile token amount, fiat obligation, verified payment, released amount, fees, timestamps, and recipient. Money fields are integer strings/bigints with schema-defined decimals. Do not convert arbitrary monetary values through JavaScript
Number. - Compare indexed observation with confirmed receipts/live contract state. Record the latest indexed evidence/block available. If the indexer lags, retry bounded reads; a lagging null is inconclusive, not a failed transaction or permission to replay it.
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.
- 9d ago Changed c6b851c6e365
- 1mo ago Changed ef0c47b696cb
- 1mo ago First seen · 42 lines · 36 tokens per session scan A 4fb15cc546df
peer-protocol-trace is a skill published in the GitHub repository zkp2p/zkp2p-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 1,005 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
code-changes
Workflow for any task that ends in code changes: issue analysis or triage, pull request review comments, features, bug fixes, refactors. Invoke at the start of such a task, before reading or writing code.
nostr-addressable-event-dual-tag-query
Fix "count shows X but list shows empty" bugs when querying related events (comments, reactions, zaps, reposts) for Nostr addressable events (Kind 30000-39999). Use when: (1) REST API shows engagement count > 0 but WebSocket query returns empty, (2) Comments/reactions exist but app shows "No comments yet" or similar…
nostr-replaceable-event-mutation-overwrite
Fix silent data loss when mutating Nostr replaceable events (Kind 0 profile, Kind 3 contact/follow list, Kind 10002 relay list, etc.) in client apps. Use when: (1) Following someone wipes the user's entire follow list, (2) Updating profile metadata loses existing fields, (3) Fresh browser session or mobile login…
nostr-addressable-event-d-tag-requirement
Fix duplicate Nostr events (Kind 30000+ parameterized replaceable events) caused by missing d-tag. Use when: (1) Same content appears multiple times on relay for same pubkey, (2) Events aren't being replaced/updated as expected, (3) Publishing NIP-71 video events (Kind 34236) or other addressable events and seeing…
divine-relay-video-requirements
Fix "blocked: event rejected by relay policy" errors when publishing Kind 34236 (video) events to divine relays. Use when: (1) Kind 0 profile events succeed but Kind 34236 fails, (2) Generic policy rejection with no specific reason, (3) Video events work on other relays but fail on divine relays. The divine relay…
ndk-operation-timeout-wrapper
Fix NDK (Nostr Dev Kit) operations hanging indefinitely when relay connections stall. Use when: (1) App freezes during fetchEvents or publish calls, (2) No timeout errors despite network issues, (3) Relay connection appears stuck, (4) Using NDK with unstable or slow relays. NDK operations have no built-in timeout …