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/ssbun/csl-agent-kit/task-queuenpx skills add SSBun/csl-agent-kit --skill task-queuegit clone --depth 1 https://github.com/SSBun/csl-agent-kitWhat 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 | $0.00067 | $0.00990 |
| Opus 5 | $0.00034 | $0.00495 |
| Sonnet 5 | $0.00013 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
task-queue 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Queue
Coordinate multiple canonical tasks through the current host Agent. This is host-native interactive execution: use the host's existing tools and subagents, never nested codex exec, pi --print, pi-worker-*, a daemon, watchdog, or unattended supervisor.
Required Runtime Protocol
Resolve the collection root as the parent of this skill directory. Before forming, presenting, or accepting a Task Target, read <collection-root>/csl-tasks/shared/protocols/task-target-alignment.md in full and treat it as the authoritative detailed alignment contract. Read it again after resume or compaction when it is no longer present in context. If it is unavailable, stop before substantive work and report the missing runtime dependency.
This skill owns Queue-parent activation, the integration Target meaning, permitted lifecycle writes, and the post-alignment Queue workflow. The shared protocol owns all Task Target alignment semantics. Use node <collection-root>/csl-tasks/shared/scripts/csl-tasks.js --workspace <workspace> ... as the only task-state core.
Build the Task Graph
- Load Project Core, then read only the newest task index entries and plausible candidate owning records needed to avoid duplicate ownership.
- As soon as the request establishes a concrete multi-task outcome, create or resume one Queue parent with an initial integration Target:
create <parent-id> --title <title> --kind queue --target "T1: <integrated outcome>". Resume the parent and call the host's task-focus mechanism when available: emit the realtask_focus(<parent-id>)tool call itself—not merely plan it—in the same reply as theresume, and disclose any binding failure. If no honest integration Target can yet be stated, ask one focused question and create the parent immediately after the answer. - Apply the shared Task Target Alignment Protocol to the active parent. For this workflow, the conversational Target means the parent integration outcome and observable completion condition; before alignment, the permitted lifecycle writes are create, resume, focus, sync, and check. The gate follows activation and precedes task-direct source inspection, graph decomposition, or substantive preparation; only the protocol's focused target-forming clarification may occur within it.
- After the protocol aligns the current Target, query task-relevant Context Packs, read relevant lessons and directly relevant sources, then clarify only user-owned decisions that block a correct decomposition.
- Refine the parent's integration Targets and create a child only for an independently acceptable or independently blocked outcome. Each child has its own observable Targets and complete
tasklifecycle. - Link children in execution order with
link <parent-id> <child-id>. The core maintains reciprocal Parent/Children records, rejects multiple parents and cycles, and preserves order. - Add the parent's current Scope and Plan, then
syncandcheckevery touched record.
What ships with it
3 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.
- 2d ago First seen · 50 lines · 67 tokens per session scan A 59c25fd5ca05
task-queue is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 990 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…