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/bierlingm/spikes/worker-fullstacknpx skills add bierlingm/spikes --skill worker-fullstackgit clone --depth 1 https://github.com/bierlingm/spikesWhat 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 | $0.00021 | $0.01150 |
| Opus 5 | $0.00010 | $0.00575 |
| Sonnet 5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
worker-fullstack 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fullstack Worker
NOTE: Startup and cleanup are handled by worker-base. This skill defines the WORK PROCEDURE.
When to Use This Skill
Features that touch documentation, site content, npm packages, or span both repos. This includes:
- Site content (llms.txt, agents.md, llms-full.txt)
- npm package creation (spikes-mcp wrapper)
- Registry manifests (smithery.yaml)
- Documentation updates
- CI/CD workflow configuration
Work Procedure
-
Read the feature description thoroughly. Understand what's being changed and in which repo(s).
-
For widget changes:
- Read
./widget/spikes.js(the source of truth) - Make changes to
widget/spikes.js - Copy to
site/spikes.js(CDN copy) if it exists - Verify widget size:
gzip -c widget/spikes.js | wc -c— must stay under 15KB - Test manually:
cd cli && cargo run -- serve --port 3847, open browser, verify behavior - Use agent-browser to verify interactive behaviors (toasts, dedup, z-index)
- Read
-
For CI/CD changes:
- Read existing workflows in
.github/workflows/(both repos) - Make changes to workflow YAML files
- Validate YAML syntax
- Test locally if possible (e.g., run the test commands that CI would run)
- Read existing workflows in
-
For documentation:
- Create or update markdown files in
./docs/ - Ensure all CLI commands are accurate by running
spikes <cmd> --help - Ensure all widget attributes are accurate by reading
widget/spikes.js - Cross-reference with actual behavior
- Create or update markdown files in
-
For dependency cleanup:
- Edit
cli/Cargo.tomlto remove crates - Remove all source files that import the removed crates
- Remove module declarations in
mod.rsandmain.rs - Run
cd cli && cargo build— must succeed with no errors or warnings - Run
cd cli && cargo test— all existing tests must still pass
- Edit
-
For test infrastructure:
- Create
vitest.config.tsin../spikes-hosted/worker/ - Create
tsconfig.jsonin../spikes-hosted/worker/ - Create test helper files in
../spikes-hosted/worker/test/ - Add dev dependencies to
package.json - Verify:
cd ../spikes-hosted/worker && npx vitest runpasses
- Create
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 · 98 lines · 21 tokens per session scan A 796a91c7a485
worker-fullstack is a skill published in the GitHub repository bierlingm/spikes (1 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,150 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 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…