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 agentmods add skills/zalom/plastic/autonpx skills add zalom/plastic --skill autogit clone --depth 1 https://github.com/zalom/plasticWhat 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 | $0.00053 | $0.06282 |
| Opus 5 | $0.00026 | $0.03141 |
| Sonnet 5 | $0.00011 | $0.01256 |
| Haiku 4.5 | $0.00005 | $0.00628 |
Grade A, and why
plastic-auto 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.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto - Autonomous Intent Delivery
Announce: "Taking over intent [ID] - [name] for autonomous delivery."
Advisory (not a gate). At auto-mode start, recommend once that the user run this
orchestrating main session on the best available thinking model (Fable, Opus, or whatever
supersedes them) for the sharpest gating and synthesis. This is advice only: it changes no
behavior and blocks nothing if ignored. It concerns the human's MAIN session; dispatched
subagents keep their pinned tier and never resolve to Fable, unless an explicit
agents.models.<name> config override names Fable for that role, in which case the override
is honored as written. The two advisors, plastic-advisor and plastic-faux-advisor, are not
lifecycle stage roles: the never-Fable rule governs stage agents only. Neither is ever
dispatched by the auto pipeline; they are consultation roles summoned deliberately by the user
or the main session, and their models are user configuration (fable and opus by default on
Claude Code).
Precondition
An active intent MUST exist in INDEX.md. If none exists, refuse: "No active intent found. Create one first with /plastic-intent-creating."
If multiple active intents exist, ask the user which one to deliver (the one question auto asks at boarding, before delivery starts).
Picking work when no intent is specified. If the user says "auto" without naming an intent and none is active, consult the roadmap first (the primary planning surface), then fall back to the dashboard queue. Read the tier's mid-flight roadmap:
ruby ~/.plastic/scripts/roadmap-next --roadmaps-dir <tier>/roadmaps
Branch on state:
dispatchable: work itsdispatchable_queueinrankorder (the head is the next batch entry). These are the current batch'squeuedintents, parallel-safe within the batch.in_flight: the frontier batch is still delivering. Report it and wait. Do NOT dispatch a later batch and do NOT fall through to the dashboard, the roadmap is live.noneorexhausted: no roadmap, or nothing left to dispatch. Fall back to the dashboard queue below. (The global store has no roadmap, so it always reportsnoneand falls back.)
What ships with it
6 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.
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.
- 2d ago First seen · 392 lines · 53 tokens per session scan A 6d71dc11b707
plastic-auto is a skill published in the GitHub repository zalom/plastic (10 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 6,282 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-reproduce-feature
Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
workflow-runner
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。.
om-create-agents-md
Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, the Always/Ask First/Never/Validation Commands boundary structure, MUST-style rules…
agent-eval-canvas
Create a BitFun Canvas for single-case agent evaluation and trajectory diagnosis. Use when the user asks to analyze one agent run, trace, case, benchmark item, failure trajectory, eval result, or critical failure step, and wants an incident-review style report covering verdict, step timeline, root cause, error…
record-and-replay
Use when the user wants Codex to record a Linux desktop or browser workflow and turn it into a reusable skill. Requires the Record & Replay event-stream MCP server.