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 jscraik/Agent-Skills --skill plugin-buildergit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/plugin-builder)<a href="https://agentmods.dev/skills/jscraik/agent-skills/plugin-builder"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/plugin-builder/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/jscraik/agent-skills/plugin-builder"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/plugin-builder.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 | $0.00042 | $0.01281 |
| Opus 5 | $0.00021 | $0.00641 |
| Sonnet 5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
plugin-builder 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 8d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Builder
Philosophy
- Validate the package boundary first; make install, release, or runtime claims only after the matching gate passes.
When to Use
Use for plugin scaffold conversion, hardening, and contract validation.
Route elsewhere:
- first shell only ->
[[plugin-creator]] - install/discovery ->
[[plugin-installer]]
Inputs
- source path or plugin path
- requested mode:
scaffold|convert|harden - marketplace requirements (if any)
Execution Boundaries
- Own plugin contract review, bundled hook validation, minimal remediation, validation evidence, and final hardening handoff.
- Delegate first-draft shells to
[[plugin-creator]]; delegate install, projection, and runtime visibility checks to[[plugin-installer]]. - Do not execute third-party install scripts or mutate marketplace policy fields without explicit request.
- Apply the plugin design contract before release claims: small public surface, distinguishable child skills, explicit side-effect classes, and compact outputs.
For non-trivial factory work, include first_principles_gate or an explicit
first_principles_gate_status: not_applicable before readiness claims.
Outputs
Return: schema_version, execution_mode, plugin_path, validation, artifacts, optional blocked_by.
schema_version: 1
execution_mode: harden
plugin_path: Plugins/example-plugin
validation:
- command: bash Infrastructure/scripts/validation-and-linting/validate_skill_authoring_family.sh
status: pass
artifacts:
- Plugins/example-plugin/.codex-plugin/plugin.json
blocked_by: null
Workflow
- Confirm mode:
scaffold,convert, orharden, plus plugin source path and write authority. - Inspect
.codex-plugin/plugin.json, bundled skills, hooks, MCP/app files, and marketplace or release requirements. - Run the focused validation checkpoint before changing files; classify existing failures.
- Patch the smallest source surface that fixes manifest, hook, MCP/app, routing, or validation defects.
- Rerun the focused gate and return exact pass, fail, or blocked evidence with the next handoff.
What ships with it
19 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.
- .skillignore 228 B
- agents/openai.yaml 327 B
- assets/icon-small.png 3.1 KB
- assets/icon.png 30 KB
- references/contract.yaml 1.8 KB
- references/current-codex-plugin-runtime.md 2.6 KB
- references/evals.yaml 4.8 KB
- references/hooks-contract.md 4.3 KB
- references/hooks.template.json 681 B
- references/plugin-contract.md 16 KB
- references/task-profile.json 1.4 KB
- references/terminology-map.md 2.6 KB
- references/workflow.md 3.2 KB
- scripts/check_plugin_builder_template_drift.py 3.7 KB runs code
- scripts/plugin_builder.py 260 B runs code
- scripts/plugin_builder.pyw 159 KB
- scripts/render_plugin_builder_templates.py 5.7 KB runs code
- templates/hooks.json.tmpl 678 B
- tests/test_wrappers.py 2.2 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.
- 8d ago First seen · 172 lines · 42 tokens per session scan A 5b0f6127a786
plugin-builder is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,281 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 2026-09-03.
Other skills, from other repositories
ad-creative
Plan and produce advertising concepts, copy variants, visual directions, and test matrices for paid campaigns.
humanizer-zh
Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.
skill-creator
Design and write concise reusable KunAgent skills with valid triggers, real tools, and testable completion criteria.
daily-brief
Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.
imf-data
Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.
scholar-research
Search, screen, synthesize, and cite scholarly literature and author metadata.