A workflow for adding one Claude Code plugin to a Hermes installation. Hermes is a command-line tool that manages plugins through a file named plugin-sync.yaml.

Use it to add, install, register, or synchronize one plugin from a repository. It collects the repository URL, branch, layout details, and Hermes location, then stops for approval before syncing.

It checks the required setup and shows the proposed configuration change before synchronization. This lets the user approve the plugin entry before any sync is run.

add-plugin — Skill by futuretyler

Install

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.

agentmods

npx agentmods add skills/futuretyler/hermetic/add-plugin

Any agent

npx skills add futuretyler/hermetic --skill add-plugin

Clone the repo

git clone --depth 1 https://github.com/futuretyler/hermetic

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00089	$0.01311
Opus 5	$0.00044	$0.00656
Sonnet 5	$0.00018	$0.00262
Haiku 4.5	$0.00009	$0.00131

Measured 2d ago against content hash 9f4128a96b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

add-plugin scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/hermetic-probe

.claude/skills/add-plugin/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a plugin via hermetic

Walks the user through appending one new plugin entry to an existing plugin-sync.yaml, then running hermetic sync. The skill stops and shows the diff before any network or filesystem work — the user must explicitly approve the YAML change before hermetic sync runs.

Preconditions (verify before anything else)

hermetic is installed. Run hermetic --version. If missing, tell the user to uv pip install hermetic-cli (or pip install hermetic-cli) and stop.
A plugin-sync.yaml exists. Check, in order:
- the path the user named in their message
- ./plugin-sync.yaml (cwd)
If neither exists, ask the user where the config lives or should be created. Do not guess a path.
Hermes home is resolved. Priority: --hermes-home flag in play > $HERMES_HOME env var > default ~/.hermes. Name the resolved path in the approval summary so the user can confirm.

Gather plugin details

Collect (ask only what the user hasn't already told you):

Repo URL — required. Any URL git clone accepts (https, ssh, file://).
Branch — default main. Don't prompt unless the user mentioned a non-default.
Monorepo layout? — many Claude Code plugin repos nest plugins under plugins/<name>/. See "Monorepo detection" below.
Plugin name — the subdirectory created under <hermes_home>/skills/<name>/. Prefer the user's stated name; otherwise use the monorepo subdir leaf or the repo's last path segment.

Monorepo detection

If the user already knows the layout, use what they said. Otherwise, the cheapest probe is a shallow treeless clone:

git clone --depth 1 --filter=tree:0 <url> /tmp/hermetic-probe
ls /tmp/hermetic-probe              # skills/ and agents/ at root?
ls /tmp/hermetic-probe/plugins 2>/dev/null  # monorepo layout?
rm -rf /tmp/hermetic-probe

skills/ and/or agents/ at the root → no subdir: needed.
plugins/<name>/ tree → set subdir: plugins/<name>.
Neither obvious → ask the user.

Read the full file on GitHub · 127 lines

Changes

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 · 127 lines · 89 tokens per session scan C 9f4128a96b24

Subscribe to this mod's changes

add-plugin is a skill published in the GitHub repository futuretyler/hermetic (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,311 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

add-plugin