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/kreek/consult/async-systemsnpx skills add kreek/consult --skill async-systemsgit clone --depth 1 https://github.com/kreek/consultWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kreek/consult/async-systems)<a href="https://agentmods.dev/skills/kreek/consult/async-systems"><img src="https://agentmods.dev/badge/skills/kreek/consult/async-systems.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00023 | $0.00900 |
| Opus 5 | $0.00012 | $0.00450 |
| Sonnet 5 | $0.00005 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
async-systems 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Async Systems
Iron Law
EVERY ASYNC BOUNDARY NAMES OWNERSHIP, LIFETIME, BACKPRESSURE, AND FAILURE SEMANTICS.
When to Use
- Designing or reviewing async execution, background work, live updates, streams, brokers, ordering, and backpressure.
- Investigating races, deadlocks, stuck tasks, starvation, retry exhaustion, dead jobs, lag, poison messages, or delivery issues.
When NOT to Use
- Request/response API design; use
api. - Remote-call timeout and retry policy; use
error-handling. - Metrics, alerts, runbooks; use
observability. - Transaction isolation; use
database.
Rules
- For user-facing live updates, start with polling, SSE, or WebSockets. Escalate to Kafka, Kinesis, or Redis Streams only after naming the requirement the simpler transport cannot meet: independent replay, long retention, audit history, offline catch-up, multi-service fanout, consumer-group scaling, partitioned throughput, or durable recovery. Record that requirement with the choice.
- Immutable data crosses async boundaries; mutable state has one owning scope. Job payloads carry stable identifiers and immutable inputs, never live session, request, or thread-local state.
- Every spawned task belongs to a scope that cancels, awaits, or supervises it, with a deterministic shutdown path.
- Every queue, channel, pool, stream, and buffer has a bound and an overflow policy. Blocking work cannot starve latency-sensitive work.
- Locks are an escape hatch: short, globally ordered, and never held across I/O, awaits, or user callbacks.
- Retried jobs and stream consumers are idempotent, deduplicated, or marked
non-retryable with a reason. Retry policy itself belongs to
error-handling. - Event schemas are contracts: versioned, consumer-compatible, and routed
through
contract-firstwhen durable. Delivery guarantee, ordering key, retention, replay, ack/offset, DLQ, and poison-message handling are explicit for streams. - Silent async failure is a bug. Exhausted jobs, lag, dropped events, and dead work have visible signals and tests.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -62 lines 115a81e77585
- 4d ago First seen · 142 lines · 23 tokens per session scan A 2165e803a3f1
async-systems is a skill published in the GitHub repository kreek/consult (1 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 900 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
migrate
Inventory an existing spec-driven project and apply bounded migrations to jig defaults: report, adopt-layout, rename-decisions, split-slices, slice-to-spec, seed-decisions, and copy-machinery. Use when the user says migrate this project to jig, adopt jig here, this repo already has specs — set up jig, scaffold-init…
bug-fix
Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOTCAUSED → FIXING → REVIEWED → DONE, with VERIFIED, ESCALATED, and RESOLVEDONMAIN paths where needed. Auto-fires on fix this bug, debug this, root-cause this, this regressed…
adr-workflow
Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…
analyze
Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity, underspecification, principle violations, coverage gaps, and terminology drift. Auto-triggers when you say analyze this spec, check for inconsistencies, audit…
explain
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…
reframe
Re-baseline a jig corpus onto a moved load-bearing reference by drafting a keystone ADR and an affected-artifact disposition manifest. Use when a vendor/API contract moved and specs and decisions must be re-anchored. Auto-triggers when you say reframe onto this, we changed direction, the design moved, or re-baseline…