CHEATSHEET

A reference sheet for the core parts of a PHP package that runs software agents. It maps the agent loop, runtime state, tools, messages, and event handling to the package code.

In plain words
What is it for?
Locating APIs and understanding how agents execute, store state, use tools, process messages, and emit events.
Why use it?
It gives developers a quick way to find the right package components without reading all of its documentation first.

Agent

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.

agentmods
npx agentmods add agents/cognesy/instructor-php/cheatsheet
Clone the repo
git clone --depth 1 https://github.com/cognesy/instructor-php
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.09736
Opus 5 $0.00009 $0.04868
Sonnet 5 $0.00004 $0.01947
Haiku 4.5 $0.00002 $0.00974

Measured 2d ago against content hash 7a85ce0733eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CHEATSHEET 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 2d 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.

packages/agents/CHEATSHEET.md · 657 lines

How it starts

The opening of the file, as written. The whole thing — 657 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Package Cheatsheet

Root namespace: Cognesy\Agents

This file is a quick, code-aligned map of the package surface. For narrative guidance and examples, use packages/agents/docs/*.md.

1. Core Loop

  • AgentLoop (readonly)
    • main orchestrator, implements CanControlAgentLoop and CanAcceptEventHandler
    • key API: default(), execute(), iterate()
    • accessors: tools(), toolExecutor(), driver(), eventHandler(), interceptor()
    • composition API: withTool(), withTools(), withDriver(), withToolExecutor(), withInterceptor(), withEventHandler(), with()
    • event API: wiretap(), onEvent()
    • note: terminal executions are auto-reset on entry to execute() / iterate()
  • CanControlAgentLoop
    • contract: execute(AgentState): AgentState, iterate(AgentState): iterable

2. State Model

  • Data\AgentState
    • immutable runtime state
    • factories: empty(), fromArray()
    • identity: agentId(), parentAgentId(), llmConfig(), executionCount(), createdAt(), updatedAt()
    • common mutators: withUserMessage(string|\Stringable|Message), withSystemPrompt(string|\Stringable), withMetadata(), withMessages(), withMessageStore(), withLLMConfig(), with()
    • step mutators: withCurrentStep(), withCurrentStepCompleted(), withExecutionCompleted(), withExecutionContinued()
    • stop/failure: withStopSignal(), withFailure(), withExecutionStatus()
    • context access: context(), store(), messages(), metadata()
    • result access: finalResponse(), currentResponse(), hasFinalResponse()
    • execution access: execution(), status(), stepCount(), steps(), usage(), errors(), hasErrors()
    • last-step accessors: lastStep(), lastStepExecution(), lastStepToolExecutions(), lastToolExecution(), lastStepErrors(), lastStepType(), lastStepUsage(), lastStepDuration()
    • stop accessors: stopSignal(), stopReason(), stopSource()
    • control: shouldStop(), forNextExecution()
    • serialization: debug(), toArray(), fromArray()
  • Data\ExecutionState
    • per-execution transient state (executionId, status, steps, continuation)
  • Data\AgentStep
    • one loop step snapshot (inputMessages, outputMessages, inferenceResponse, toolExecutions, errors)
  • Data\StepExecution
    • completed step wrapper with timing
  • Data\ToolExecution
    • one executed tool call (value(), hasError(), errorAsString(), wasBlocked())
  • Data\ExecutionBudget
    • optional limits: maxSteps, maxTokens, maxSeconds, maxCost, deadline
    • factories: unlimited()
    • queries: isEmpty(), isExhausted()
  • Data\AgentId, Data\ExecutionId, Data\AgentStepId, Data\ToolExecutionId
    • typed ID value objects

Read the full file on GitHub · 657 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. 2d ago First seen · 657 lines · 18 tokens per session scan A 7a85ce0733eb

Subscribe to this mod's changes

CHEATSHEET is an agent published in the GitHub repository cognesy/instructor-php (326 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 9,736 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 2026-08-30.