Borrowing it
Nothing to install: this file belongs to Foxfire1st/agents-remember. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Foxfire1st/agents-remember/main/.agents/skills/l-01-agent-lifecycles/SKILL.mdgit clone --depth 1 https://github.com/Foxfire1st/agents-rememberWrote 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/foxfire1st/agents-remember/l-01-agent-lifecycles)<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/l-01-agent-lifecycles"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/l-01-agent-lifecycles/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/foxfire1st/agents-remember/l-01-agent-lifecycles"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/l-01-agent-lifecycles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00135 | $0.07451 |
| Opus 5 | $0.00068 | $0.03726 |
| Sonnet 5 | $0.00027 | $0.01490 |
| Haiku 4.5 | $0.00014 | $0.00745 |
Grade A, and why
l-01-agent-lifecycles 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 10d 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
l-01-agent-lifecycles — The Agent Lifecycles
Lifecycle and job are one entity: each agent type runs its own, self-contained lifecycle. This skill is the single roof over all of them — a thin router, the minimal frame every session shares, and the role lifecycles as the payload files. No role is defined by reference to another role's lifecycle, and no role reads another role's file.
Which Lifecycle Am I? (the router — exactly three conditions, in order)
AR_SPAWN_ROLEis set (injected by the hosted-seat control plane) → runroles/<value>.md. Nothing else in this file's "developer session" material applies to you. (designerhere means the same design hat in a separate chair — seeroles/designer.md.)- Else: the first user message is a role brief in a fresh session — a
templates/*-brief.md-shaped dispatch or a first line of the formROLE BRIEF — <role>from an orchestrating agent → run that role's lifecycle. The brief is your session start; a workspace session-start notice is not addressed to you. - Else (a developer opened this session) → you are the developer-facing free chat — a
launcher, not a role seat (ruled 2026-07-09). Research-only questions are answered inline with
no role taken. The moment the ask is role-shaped (a sprint, a task, any durable change), do NOT
assume the architect role in this chat: resolve the target sprint, then open that sprint in
Operations and use its role control to create or switch to the architect chat bound to the
sprint document. The dashboard and control plane choose the runtime occupant and inject the
role; this launcher never handles a session id. The architect profile — harness/model/effort —
comes from
orchestration.roles.architectin settings. The resulting architect runsroles/architect.mdand owns that sprint's developer conversation. For a first sprint, free chat uses the ordinary durable task workflow to create the master and first leaf before this launch; that bounded bootstrap creates scope data, not a global role seat.
What ships with it
26 files 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.
- criteria/code-seam.md 7.8 KB
- criteria/doctrine.md 3.2 KB
- criteria/onboarding-memory.md 4.0 KB
- criteria/plan-review.md 5.6 KB
- criteria/report-verification.md 6.2 KB
- lenses.md 2.9 KB
- roles/architect.md 18 KB
- roles/curator.md 15 KB
- roles/designer.md 6.8 KB
- roles/manager.md 21 KB
- roles/orchestrator.md 34 KB
- roles/reviewer.md 14 KB
- roles/strategist.md 13 KB
- roles/system-specialist.md 4.8 KB
- roles/worker.md 11 KB
- templates/conversation-handover-packet.md 2.4 KB
- templates/curator-brief.md 11 KB
- templates/deep-research-report.md 3.9 KB
- templates/impact-analysis.md 2.3 KB
- templates/manager-brief.md 6.3 KB
- templates/master-handover-packet.md 2.3 KB
- templates/onboarding-coherency.md 2.1 KB
- templates/orchestration-task.md 5.9 KB
- templates/turn-report.md 2.3 KB
- templates/verdict.md 10.0 KB
- templates/worker-brief.md 5.2 KB
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.
- 10d ago First seen · 449 lines · 135 tokens per session scan A c69d59e3e061
l-01-agent-lifecycles is a skill published in the GitHub repository Foxfire1st/agents-remember (27 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 7,451 once invoked, about $0.0007 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.
Other skills, from other repositories
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…