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.
npx skills add electronick1/LLAssemblyCLI --skill common_skill_partsgit clone --depth 1 https://github.com/electronick1/LLAssemblyCLIWrote 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/electronick1/llassemblycli/common_skill_parts)<a href="https://agentmods.dev/skills/electronick1/llassemblycli/common_skill_parts"><img src="https://agentmods.dev/badge/skills/electronick1/llassemblycli/common_skill_parts/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/electronick1/llassemblycli/common_skill_parts"><img src="https://agentmods.dev/badge/skills/electronick1/llassemblycli/common_skill_parts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.02370 |
| Opus 5.5 | $0.00024 | $0.00948 |
| Sonnet 5.5 | $0.00012 | $0.00474 |
| Haiku 4.5 | $0.00006 | $0.00237 |
Grade A, and why
llassembly-agentic-workflow 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 1mo 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLAssembly agentic workflow
This skill executed in three roles below:
ORCHESTRATOR — the session where the user asked you to run this skill. You do not do the
the actual work and you do not write files - you run scripts/get_next_instruction.py
— a resumable state machine, called the driver, that prints next instructions to execute.
You perform these instructions, then you run the driver again. Repeat without stopping
until the driver prints that execution is finished.
WORKER — an agent the orchestrator spawned at Stage 2 or Stage 3. You write ONE file:
the control-flow plan, or one sub-agent definition file. Then you exit. You never run
scripts/get_next_instruction.py.
SUB-AGENT — an agent the orchestrator spawned at Stage 5 to perform requested work.
You execute what is requested, write ONE result JSON file based on the JSON schema
specified. Then you exit. You never run scripts/get_next_instruction.py.
Arguments and environment
--llassembly-session <id>— identifies this workflow session; every file and every log record is keyed by it. You must type the id the driver gave you on every execution, written as an argument after the command:python scripts/get_next_instruction.py --llassembly-session <id>.LLASSEMBLY_WORKFLOW_PATH— base directory for workflow workspaces, supplied by the environment (default/tmp). Leave it as you found it; setting it moves the whole workflow.
Execution protocol for worker and sub-agent:
If you are a WORKER or a SUB-AGENT, open the one file your dispatch named, do instructed scope of work, report / write results and exit. You never perform orchestrator duty.
Execution protocol for orchestrator:
These stages are the ORCHESTRATOR's protocol. A WORKER or a SUB-AGENT never performs them.
SPAWN A NEW AGENT
Every instruction given from the driver that says SPAWN A NEW AGENT means: use your agent-spawning tool to start a separate, standalone, independent agent that receives only the prompt text you write, does the work on its own, and exits — never you, never a continuation of an agent that already ran, never a to-do / checklist / task-list entry.
What ships with it
24 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.
- assets/command_stage_1/get_context.txt 329 B
- assets/command_stage_1/workflow_id_init.txt 453 B
- assets/command_stage_1/workflow_id.txt 420 B
- assets/command_stage_2/create_plan.txt 1.9 KB
- assets/command_stage_3/generate_sub_agent_item.txt 142 B
- assets/command_stage_3/generate_sub_agent.txt 2.2 KB
- assets/command_stage_4/save_exists.txt 151 B
- assets/command_stage_4/save_invalid_cli.txt 238 B
- assets/command_stage_4/save_invalid.txt 225 B
- assets/command_stage_4/saved.txt 95 B
- assets/command_stage_5/execute_sub_agent.txt 2.4 KB
- assets/command_stage_5/finished.txt 343 B
- assets/command_stage_5/incorrect_sub_agent_results.txt 939 B
- assets/fallback_cases/emulator_unimportable.txt 478 B
- assets/fallback_cases/plan_load_failed.txt 399 B
- assets/llassembly-claude-workflow.js 10 KB runs code
- references/agent_generator_helpers/coding.md 1.2 KB
- references/agent_generator_helpers/diagnosis.md 992 B
- references/agent_generator_helpers/research.md 2.3 KB
- references/agent_generator_helpers/testing.md 978 B
- references/agent_generator_helpers/verification.md 1.2 KB
- references/prebuilt-skill.md 1.4 KB
- references/workers/llassembly-generate-sub-agents.md 6.4 KB
- scripts/get_next_instruction.py 29 KB runs code
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.
- 1mo ago First seen · 195 lines · 60 tokens per session scan A 5346808c286f
llassembly-agentic-workflow is a skill published in the GitHub repository electronick1/LLAssemblyCLI (7 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 2,370 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, and a dashboard of gauges for a system snapshot, a…
penguin-plugin
Use for workbenches — the tabs and pages beside the chat, with server code behind them, that an Agent keeps in its own workbenches/ folder inside PenguinHarness — building one, changing it, showing it as the whole app, restoring an earlier version, and removing a tab or a whole workbench when the user wants the custom…
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…