instruction-introspection

instruction-introspection is a skill for Claude Code, Codex from PlamenTSV/plamen. It costs 34 tokens per session (1,141 once invoked), scanned A, original, MIT.

A security review guide for Solana instruction introspection, which reads other instructions in the same transaction. It focuses on validating the special account that stores those instructions.

In plain words
What is it for?
It helps list introspection usage, check the source and address of the instructions account, and flag missing validation.
Why use it?
It helps prevent attackers from supplying a fake instructions account and making the program read data they control.

Skill for Claude CodeCodex

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

Good fit It helps list introspection usage, check the source and address of the instructions account, and flag missing validation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plamentsv/plamen/instruction-introspection
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 instruction-introspection
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 instruction-introspection

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/plamentsv/plamen/instruction-introspection"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/instruction-introspection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 $0.00034 $0.01141
Opus 5 $0.00017 $0.00571
Sonnet 5 $0.00007 $0.00228
Haiku 4.5 $0.00003 $0.00114

Measured 7d ago against content hash 0e3030cc9195, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

instruction-introspection 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 7d 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/solana/instruction-introspection/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

INSTRUCTION_INTROSPECTION Skill

Trigger Pattern: INSTRUCTION_INTROSPECTION flag detected (load_instruction_at/Sysvar1nstructions) Inject Into: Breadth agents, depth agents Finding prefix: [II-N] Rules referenced: S10, S8, R15

For every use of instruction introspection in the Solana program:

1. Introspection Usage Inventory

List all instruction introspection usage:

# Location Function Used Purpose Instructions Sysvar Source
1 {file:line} load_instruction_at_checked / load_instruction_at / get_instruction_relative {what it checks} {account source}

2. Sysvar Address Validation (Wormhole Pattern - CRITICAL)

For each Instructions sysvar account:

Usage Sysvar Source Address Validated? Validation Method
{usage} {account param name} YES/NO {hardcoded check / Anchor constraint / NONE}

Attack pattern (sysvar address spoofing): If Instructions sysvar address is NOT validated, attacker passes a fake account containing crafted "instruction" data. The introspection reads attacker-controlled data instead of real transaction instructions. Defense: require!(sysvar_account.key() == sysvar::instructions::ID) or use Anchor #[account(address = sysvar::instructions::ID)].

3. Checked Function Usage

For each load_instruction_at* call:

Call Uses _checked Variant? Risk if Unchecked
{call} YES/NO {if NO: deprecated function, potential ABI issues}

Rule: Always use load_instruction_at_checked (validates the sysvar account) over the deprecated load_instruction_at (does not validate).

4. Instruction Sequence Validation

For flash loan and atomic operation patterns:

Pattern Borrow Instruction Checked? Repay Instruction Checked? Gap Between Checks?
Flash loan repay check YES/NO YES/NO {can attacker insert instructions between borrow and repay?}

Read the full file on GitHub · 100 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. 7d ago First seen · 100 lines · 34 tokens per session scan A 0e3030cc9195

Subscribe to this mod's changes

instruction-introspection is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,141 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 2026-09-03.

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