agent-lifecycle

A guide to the stages an AI agent goes through while handling a task, from setup through execution. It describes the task object, its inputs, memory, tools, and lifecycle hooks—code that runs at particular stages.

In plain words
What is it for?
Use it when building or debugging Synapse agents, especially when adding inputs, reading task memory, accessing tools, or changing lifecycle stages.
Why use it?
It helps developers understand where to inspect or change an agent’s behavior during a run.

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/usethefork/synapse/agent-lifecycle
Clone the repo
git clone --depth 1 https://github.com/UseTheFork/synapse
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 867 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 $0.00000 $0.00867
Opus 5 $0.00000 $0.00434
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00087

Measured yesterday against content hash 4cabd546d31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-lifecycle 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 yesterday.

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.

docs/agents/agent-lifecycle.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Lifecycle

One of the most powerful features of Synapse is the Agent Lifecycle, which governs how an agent executes its tasks and allows for modification at various stages.

PendingAgentTask

The PendingAgentTask class drives the agent's execution and stores all information about the current run. This class provides several public methods that can be accessed and modified:

  • addInput(string $key, mixed $value): Adds an input to the array used to generate the prompt.
  • agent(): Returns the agent instance.
  • currentIteration(): Returns the CurrentIteration object containing the raw response and message.
  • inputs(): Retrieves the current input array.
  • getInput(string $key): Retrieves a specific input by key.
  • iterationMemory(): Accesses the agent's memory for the current task.
  • tools(): Retrieves the tools available to the agent.

Lifecycle

The agent lifecycle is divided into the following stages:

Initialize Agent

The agent is set up, and all hooks are initialized.

To modify the agent at this stage, use the HasBootAgentHook in the Hook Traits section.

Code Calls the handle Method

The handle method is invoked, a new CurrentIteration is created, and the inputs and extraAgentArgs are set.

$simpleAgent = new SimpleAgent;
$result = $agent->handle(['input' => 'hello!'], ['model' => 'gpt-4o-mini']); // [!code highlight]

To modify the agent at this stage, use the HasStartThreadHook in the Hook Traits section.

Start 'Iteration Loop'

The 'Iteration Loop' begins by executing the StartIterationPipeline. Each loop iteration triggers all pipelines, which are executed multiple times if the agent calls multiple tools.

To modify the agent at this stage, use the HasStartIterationHook in the Hook Traits section.

Get Prompt

The agent combines the view with inputs to create the prompt.

To modify the agent at this stage, use the HasPromptGeneratedHook in the Hook Traits section.

Read the full file on GitHub · 85 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. yesterday First seen · 85 lines · 0 tokens per session scan A 4cabd546d31f

Subscribe to this mod's changes

agent-lifecycle is an agent published in the GitHub repository UseTheFork/synapse (50 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 867 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 2026-08-30.

Related

Other agents, from other repositories