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/abilityai/abilities/add-pipeline-instancenpx skills add Abilityai/abilities --skill add-pipeline-instancegit clone --depth 1 https://github.com/Abilityai/abilitiesWhat 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 | $0.00057 | $0.01515 |
| Opus 5 | $0.00028 | $0.00758 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
add-pipeline-instance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Pipeline Instance
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.add-pipeline-instance vX.Y — recent: <summary>. Then proceed.
Add an independent runtime instance to an existing pipeline. Each instance runs the same DAG with its own state and config — a zone, a tenant, a case, a customer.
The pipeline is the DAG. The instance is who the DAG runs for.
Process
Step 1: Resolve pipeline + instance slug
Expect <pipeline-slug> <instance-slug> as positional args. If missing, prompt.
Validate:
projects/<pipeline-slug>/pipeline.yamlexists (else suggest/add-pipeline).<instance-slug>matches^[a-z][a-z0-9-]{1,40}$.projects/<pipeline-slug>/instances/<instance-slug>/does not already exist (else refuse — picking a new slug, or use/pipeline-resumeif you meant to reactivate).
Step 2: Optional — clone from an existing instance
If --from <existing-instance> was passed, copy that instance's config.yaml as the starting point. Useful when most fields are identical across tenants/zones.
SRC="projects/$PIPELINE/instances/$FROM/config.yaml"
[ -f "$SRC" ] || error "Source instance not found"
mkdir -p "projects/$PIPELINE/instances/$INSTANCE"
cp "$SRC" "projects/$PIPELINE/instances/$INSTANCE/config.yaml"
Otherwise, scaffold a minimal config.yaml:
# Instance config for <INSTANCE> in pipeline <PIPELINE>
status: active # active | inactive — controls whether heartbeat evaluates
name: "<Human Name>"
# Per-instance overrides — merge over pipeline.yaml defaults.
# Common keys: sources, tags, filters, schema, PIRs, target outputs.
# Add what your stages need:
overrides: {}
Step 3: Ask config questions
These are intentionally minimal — instance-specific fields depend on the pipeline. Ask only what the pipeline needs.
Q1 — Display name (free text)
- "Human-readable name for this instance."
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 · 149 lines · 57 tokens per session scan A 7ed3e2717dc6
add-pipeline-instance is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 15d ago), licensed MIT. It adds 57 tokens to every session and 1,515 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…