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/intent-linkingnpx skills add zalom/plastic --skill intent-linkinggit 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 | $0.00043 | $0.01678 |
| Opus 5 | $0.00022 | $0.00839 |
| Sonnet 5 | $0.00009 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
plastic-intent-linking 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linking Intents
When to Use
- During intent creation (automatic: ask about related intents)
- User says "link", "connect", "relates to"
- Agent discovers a relationship between intents during work
Discovery and ranking are separate
Two distinct steps, do not conflate them:
- Discovery (finding candidate related intents) may use any tool: grep, find, ripgrep, or QMD/Serena when present (QMD-first per the project rule). Discovery casts a wide net.
- Ranking the candidates is a CONTEXT-INFLUENCE judgement: read each candidate's
## Intentand## Contextand ask whether that context actually informed this intent. Ranking is NOT a structural metric (no shared-file or shared-symbol grading: on intent 90, matching whole files flagged 35 intents because ~20 touchbridge.rb). It is NOT a similarity score either (QMD relevance measures topic proximity, not influence). A script cannot make this call; an agent does.
The three tiers (by context influence)
Read ../plastic-conventions/references/knowledge-graph.md for the full linking doctrine behind
these tiers, the sources-versus-chain distinction, and the ## Links projection. This path
resolves relative to this skill's own installed directory.
- sources: the foundational context that shaped this intent's CREATION (a split, an idea born during development, a merge). Earns an edge. Decided by origin, never inferred.
- chain: the context that materially helps DELIVER this intent. HIGH bar: only the genuinely
delivery-moving intents, not everything in the same area. Earns an edge, reflected in
## Links. Worked example (intent 90): 79 created it so 79 is a source; 80 deferred the exact fix 90 makes, so its context directly helps delivery and 80 is chain; 49/66/73 are same-area background, so they get a shared tag and no link. - tags: loose theme grouping for search. NOT a link.
Timing. The influence judgement happens at What/Why (and during upkeep), guided by this rule. It does not wait for code to exist; it is reasoning over the candidate's context, not over a diff.
What ships with it
2 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.
- 3d ago First seen · 129 lines · 43 tokens per session scan A a46974c93ab4
plastic-intent-linking is a skill published in the GitHub repository zalom/plastic (10 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,678 once invoked, about $0.0002 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
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
agent-workspace-linux
Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file…
ss-component
Generate a new UI component following the StyleSeed design conventions.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.