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/gleanwork/pluginpack/add-pluginpack-targetnpx skills add gleanwork/pluginpack --skill add-pluginpack-targetgit clone --depth 1 https://github.com/gleanwork/pluginpackWhat 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 | $0.00053 | $0.00510 |
| Opus 5 | $0.00026 | $0.00255 |
| Sonnet 5 | $0.00011 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
add-pluginpack-target 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 yesterday.
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
Adding a pluginpack target
A target adapter owns one app's native layout, manifests, and validation.
First: get the real format, do not guess
Find the app's actual plugin format from official docs or a real published
plugin repo (the way the existing adapters were derived from github/copilot-plugins,
gleanwork/cursor-plugins, the Claude plugins reference, and the documented
OpenAI Codex CLI plugin format). Capture an
external oracle you can validate against — a published JSON Schema, the app's
own validator CLI, or a real repo to diff against. Record it in
CONFORMANCE.md.
Touch points
Adding a target means:
src/types.ts— add the name to theTargetNameunion.src/targets/<name>.ts— implementPluginTargetDefinition(seesrc/targets/types.ts): emit logic, manifest/marketplace builder, validation, install snippet, and defaults.src/targets/registry.ts— add one entry mapping the name to that definition.
Everything else — the CLI's --target choices, build()'s target set, and
emit/validate dispatch — derives from the registry automatically via the
shared engine in src/targets/engine.ts. Reuse src/targets/validation-shared.ts
for checks whose shape genuinely matches the other targets (hooks, frontmatter);
write your own where the shape is genuinely different, the way codex's
structured source object does.
Wire MCP
If the app supports MCP servers, decide whether it reads a .mcp.json file
(reference it from the manifest, like cursor/copilot, or rely on auto-discovery,
like claude), a target-specific config file (like Antigravity's
mcp_config.json), or another native shape. resolveMcpServers already merges
a plugin's servers; thread the result into your emitter.
Verify
Add conformance tests in tests/ against the external oracle, extend
CONFORMANCE.md, then run npm run check.
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.
- yesterday First seen · 50 lines · 53 tokens per session scan A b39385f55ca4
add-pluginpack-target is a skill published in the GitHub repository gleanwork/pluginpack (5 stars, last pushed 21d ago), licensed MIT. It adds 53 tokens to every session and 510 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…