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 zalom/plastic --skill store-provisioninggit clone --depth 1 https://github.com/zalom/plasticWrote 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/zalom/plastic/store-provisioning)<a href="https://agentmods.dev/skills/zalom/plastic/store-provisioning"><img src="https://agentmods.dev/badge/skills/zalom/plastic/store-provisioning.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00494 |
| Opus 5 | $0.00036 | $0.00247 |
| Sonnet 5 | $0.00015 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
plastic-store-provisioning 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 6d 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.
What it actually says
Add a Project Store
Provision the intent store for a project that is already registered in
projects.yml but whose ~/.plastic/projects/{slug}/store/ is missing. This is
the standalone path; plastic-project-creating provisions the store for brand
new projects.
The provisioner is the single source of truth for store creation. It is pure
filesystem and idempotent, so re-running is always safe. The project must already
be registered (this skill does not edit projects.yml).
1. Resolve the slug
The slug is the project's key under projects in ~/.plastic/projects.yml. If
the user names a project, map it to its slug. If the slug is missing from
projects.yml, stop: the provisioner requires the project to already be
registered. If ambiguous, list the registered slugs and ask which one.
2. Run the provisioner
ruby ~/.plastic/scripts/provision-project-store <slug>
This creates ~/.plastic/projects/<slug>/store/ with .gitkeep, writes
INDEX.md and project.yml only if they are missing, and never clobbers
existing files. An unregistered slug exits non-zero with a clear error and
creates nothing.
3. Register with QMD (separate, optional step)
ruby ~/.plastic/scripts/qmd-sync register --store ~/.plastic/projects/<slug>/store
This is the only qmd mutation; the provisioner itself performs none. It no-ops when qmd is absent, so it is safe to run unconditionally.
Scope
- Provisioning and qmd registration are two distinct steps. Do not fold qmd into the provisioner.
- No
projects.ymledits, no project-tree edits, no tactical-mirror or founding-intent seeding.
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.
- 6d ago First seen · 56 lines · 73 tokens per session scan A 8b27dc11924a
plastic-store-provisioning is a skill published in the GitHub repository zalom/plastic (10 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 494 once invoked, about $0.0004 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
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
compress
Use when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
session-management
Context preservation, tiered summarization, resumability.
code-graph
AST-based code graph for fast symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp MCP server.
grimoire
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.