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-contextnpx skills add SSBun/csl-agent-kit --skill task-contextgit 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 | $0.00096 | $0.02695 |
| Opus 5 | $0.00048 | $0.01347 |
| Sonnet 5 | $0.00019 | $0.00539 |
| Haiku 4.5 | $0.00010 | $0.00269 |
Grade A, and why
task-context 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Workspace Context
Purpose
Use tasks/context.md to give a newly dispatched Agent the project model needed to start a concrete task without repeating broad repository exploration, repo mapping, or architecture analysis.
Context accelerates orientation; it does not replace reading task-direct source and tests. Treat linked source, schema, configuration, ADR, SOP, rule, or formal document as authoritative. Verify task-relevant Authority before an important decision, and let Authority override stale Context.
Every workspace must have a standard Context before task dispatch. When an existing file lacks a valid Project Core, rewrite it from authoritative project sources without preserving its old content. When the file is missing, inspect the project, present a minimal Project Core proposal, and obtain explicit user confirmation before creating it. Routine context loading, bootstrap, and maintenance do not create a task record.
Data Model
Keep one canonical tasks/context.md with two layers:
Project Coreis the small project-wide model loaded at session start, resume, and compaction.Context Packsare complete task-relevant models selected after a concrete task is understood.
Do not split records into another directory or persist a generated index, query cache, or selected IDs.
Project Core
Use exactly these non-empty flat-list sections in this order:
## Project Core
### Purpose
- ...
### Global Vocabulary
- ...
### System Map
- ...
### Global Invariants
- ...
Core explains what the project is, the vocabulary needed to form a Task Fingerprint, the major system boundaries, and invariants that apply across Packs. It is not a component catalog.
Context Pack
Use a stable ASCII ID and this shape:
## CTX-ascii-slug — Title
- Scope: ...
- Paths: `path/one`, `path/two`
- Keywords: term one, term two
- Authority: `authoritative/source`
- Recheck: Concrete event that invalidates or requires verifying this Pack.
### Purpose and Boundaries
- ...
What ships with it
5 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 · 231 lines · 96 tokens per session scan A e520e3a19f32
task-context is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 2,695 once invoked, about $0.0005 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…