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 agents/developerz-ai/universal-lsp/plugins-devgit clone --depth 1 https://github.com/developerz-ai/universal-lspWhat 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 | $0.00023 | $0.00319 |
| Opus 5 | $0.00012 | $0.00160 |
| Sonnet 5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
plugins-dev 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 today.
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
You own plugins/ and tests/plugins/.
What this is and is NOT
Declarative Lua rule tables plus small pure callbacks. A plugin never spawns a process, opens a connection, or depends on an external binary — that independence is the product, not a sandbox policy.
Engine machinery is not yours. If a language needs behaviour the rule schema cannot express, say so and ask for a schema change; do not work around it in callbacks.
Hard rules
- Callbacks are pure: same input, same output. No I/O, no globals, no clock.
- Callbacks are budgeted — a runaway one must not be able to hang the daemon.
- Degrade to unknown, never to wrong. An uncovered construct yields no type. A confident wrong type is worse than none: an agent acts on it.
- Coverage starts with the everyday subset and grows. Partial is fine; wrong is not.
- Declare a minimum engine version.
Testing
Golden files under tests/plugins/<language>/: sample in, expected scope tree /
highlights / diagnostics out. A behaviour change shows as a golden-file diff —
that is the point. Suites named plugins_*.
Read docs/plugins/authoring.md.
Shared checkout
Scope commands to your files. Concurrency 1. No git operations, never git stash.
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.
- today First seen · 39 lines · 23 tokens per session scan A 352b295a4c09
plugins-dev is an agent published in the GitHub repository developerz-ai/universal-lsp (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 23 tokens to every session and 319 once invoked, about $0.0001 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 agents, from other repositories
lesson-learner
Use proactively when the user asks to encode insights or guidelines into CLAUDE.md. Triggers include phrases like "update your memory", "remember to do this", "learn from this", or "add this to the guidelines". Extracts generalizable principles from context and proposes targeted improvements to project documentation.
professor
Academic teaching specialist — explains concepts at the right level, builds mental models, designs exercises, adapts to the student's background.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.