peer-scoring-correctness

peer-scoring-correctness is a skill for Claude Code, Codex from PlamenTSV/plamen. It costs 27 tokens per session (967 once invoked), scanned A, original, MIT.

A code-audit skill for peer-scoring systems, which assign reputation points to nodes based on their behaviour. It checks whether rewards and penalties cover the same kinds of actions.

In plain words
What is it for?
It is for reviewing score changes for block validation, data requests, health checks, gossip, bootstrap, timeouts, duplicates, failures, and peer bans.
Why use it?
It helps find ways for a dishonest peer to gain trust faster than it loses it, or to avoid penalties for bad responses. That can leave a network connected to unreliable or malicious peers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing score changes for block validation, data requests, health checks, gossip, bootstrap, timeouts, duplicates, failures, and peer bans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plamentsv/plamen/peer-scoring-correctness
Install

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.

Any agent
npx skills add PlamenTSV/plamen --skill peer-scoring-correctness
Clone the repo
git clone --depth 1 https://github.com/PlamenTSV/plamen

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for peer-scoring-correctness

README.md
[![agentmods](https://agentmods.dev/badge/skills/plamentsv/plamen/peer-scoring-correctness/github.svg)](https://agentmods.dev/skills/plamentsv/plamen/peer-scoring-correctness)
Your own site
<a href="https://agentmods.dev/skills/plamentsv/plamen/peer-scoring-correctness"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/peer-scoring-correctness/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.

agentmods 80×15 button for peer-scoring-correctness

Your own site · 80×15
<a href="https://agentmods.dev/skills/plamentsv/plamen/peer-scoring-correctness"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/peer-scoring-correctness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00967
Opus 5 $0.00014 $0.00483
Sonnet 5 $0.00005 $0.00193
Haiku 4.5 $0.00003 $0.00097

Measured 6d ago against content hash 834f038e5b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

peer-scoring-correctness 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 6d 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.

agents/skills/injectable/l1/peer-scoring-correctness/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Injectable Skill: Peer Scoring Correctness

L1 trigger: P2P flag AND (score_peer, peer_score, reputation, misbehavior, ban_peer, peer_scoring detected) Inject Into: depth-network-surface Language: Go and Rust Finding prefix: [PSC-N]

1. Reward / Penalty Symmetry

Enumerate all score increments and all score decrements. For every reward path, identify the matching penalty path and ask whether a malicious peer can gain trust faster than it can lose it.

Tag: [PEER-SCORE:SYMMETRY]

Required full-leg matrix: Do not stop after the first scoring bug. Build a complete table of every score mutation and every peer-performance observation:

Leg Event / endpoint Reward? Penalty? Error classes penalized Can attacker farm?
block validation valid / invalid block
block pool / orphan handling unknown parent, invalid data, timeout
health check HTTP 200, non-200, timeout, parse error
data/chunk request delivery success, delivery fail, no response
gossip valid message, invalid message, duplicate, re-gossip
bootstrap / peer list useful peer, bogus peer, stale address

Every blank Penalty? for a harmful event is a candidate finding. Every blank Can attacker farm? for a reward event is incomplete analysis.

2. Penalty Coverage

Build a failure-mode table and verify every harmful action has a score impact:

Failure mode Penalized? Immediate? Resettable?
Invalid block / tx
Timeout / stall
Malformed gossip
Health-check failure
Excessive requests
Non-response / timeout
Non-200 HTTP response
Delivery failure after accepted request
Invalid block held in cache / orphan pool
Stale peer address update

Tag: [PEER-SCORE:COVERAGE]

3. Farming / Free-Riding

Check whether peers can cheaply farm score via ping loops, get_data style requests, acknowledgements without contribution, or reconnect-based resets. Quantify attacker cost versus defender work.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 6d ago First seen · 103 lines · 27 tokens per session scan A 834f038e5b67

Subscribe to this mod's changes

peer-scoring-correctness is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 967 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

analyzing-ethereum-smart-contract-vulnerabilities

Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.

mukul975/Anthropic-Cybersecurity-Skills · 49 tokens

prowler-tour

Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.

prowler-cloud/prowler · 41 tokens

evm-bytecode-analysis

Analyze supplied deployed EVM runtime bytecode with EVMole or guide a separate application in integrating a published EVMole Rust, Go, Python, or JavaScript binding. Use for unverified-contract inspection, ABI reconstruction from runtime code, selector discovery, storage-access analysis, EVM control-flow inspection…

cdump/evmole · 135 tokens

talos-action-development

Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…

OriginProtocol/origin-dollar · 70 tokens

web3-poc-foundry

Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.

Awarexone/web3-bug-bounty-hunting-ai-skills · 59 tokens

web3-grep-arsenal

Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.

Awarexone/web3-bug-bounty-hunting-ai-skills · 39 tokens