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/heapy/kortex/work-tasknpx skills add Heapy/kortex --skill work-taskgit clone --depth 1 https://github.com/Heapy/kortexWhat 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 | $0.00060 | $0.01029 |
| Opus 5 | $0.00030 | $0.00515 |
| Sonnet 5 | $0.00012 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
work-task 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Task
Carry one linked task from in_progress to review. Use the kotgent CLI for tracker operations and
git for repository state and history. Do not use an MCP server, SDK, direct daemon request, or helper
script for kotgent.
Read the task and repository first
Use the live kotgent pane as identity by default. Never read KOTGENT_SESSION_ID as identity or copy it
into --session. Outside a kotgent pane, require an exact session ID explicitly supplied by the invocation
context or user. Never infer one from provider conversation IDs, environment variables, names, cwd,
recency, or kotgent list. Keep one identity mode for the whole run.
Require git and kotgent, resolve the Git root, then run the pane form:
kotgent task show
Use kotgent task show --session <session-id> only in explicit outside-pane mode.
Keep task show, task comment, and task review ref-less throughout this linked-task workflow. In
explicit mode --session names the caller while the CLI still resolves that session's current task.
Stop if the session is not linked. Require the returned task state to be in_progress; send todo work
through take-task, and stop for review or done. Read the complete body, dependencies, activity, and
linked sessions.
Read applicable repository instructions before editing, especially AGENTS.md and CLAUDE.md, then any
active plan or backlog referenced by the task. Capture git status --short, branch or detached state,
full HEAD, and relevant diffs. Preserve pre-existing user changes and never sweep an untracked
.kotgent.json into an unrelated commit.
Check kotgent project list; if the task's project is archived, report that fact and do not initialize,
restore, switch, or retry. An already-linked task may still be completed through comment and review.
Coordinate before editing
Task links are non-exclusive. Treat another live, non-archived linked session, recent implementation activity from another session, or overlapping worktree changes as a coordination risk unless the user already established a division of work. Leave one evidence-rich coordination comment and stop for human direction rather than racing:
What ships with it
1 file 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.
- yesterday First seen · 102 lines · 60 tokens per session scan A 3e32de80c052
work-task is a skill published in the GitHub repository Heapy/kortex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,029 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
mobile-experience-report
Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.
motherduck-design-dive
Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…
gradle-expert
Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5)…
add-native
Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…
amy-expert
Patterns for extending amy, the Amethyst CLI in cli/. Use when adding an amy command, touching files under cli/src/main/kotlin/…/cli/, wiring a new subcommand into Main.kt, writing an interop test script that drives Amy, or extracting logic out of amethyst/ into commons/ so a CLI command can call it. Enforces the…
compose-side-effects
Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection. Technique-layer skill — complements the codebase-specific compose-expert.