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/sync-tasksnpx skills add Heapy/kortex --skill sync-tasksgit 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 | $0.00069 | $0.01094 |
| Opus 5 | $0.00034 | $0.00547 |
| Sonnet 5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
sync-tasks 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Tasks
Build an evidence-backed reconciliation report. Use the kotgent CLI for tracker reads and git plus
ordinary file inspection for repository evidence. Do not use an MCP server, SDK, direct daemon request,
or helper script.
Stay read-only
Do not run task add, task claim, task comment, task review, task done, task unlink, task move,
task dep, task delete, project init, project delete, or project restore. Do not edit repository
files. Suggested commands belong only in the report.
Treat successful task and project stdout as JSON and failure stderr as JSON. Exit 2 means this skill
built an invalid command and stderr may be plain usage text; stop and report it exactly. Never retry a
deleted-project error or restore/reinitialize a project.
Establish the project and task snapshot
- Require
gitandkotgent, resolvegit rev-parse --show-toplevel, and read the root.kotgent.json. Stop if the file is missing or itsidis not a UUID. - Read both
kotgent project listand, only if needed,kotgent project list --archived. Record whether the exact UUID is live or archived. An unknown UUID is an error. An archived project may still be read, but label it and do not propose an automatic restore. - Run
kotgent task list --project <project-uuid>. Select only rows whose state is exactlytodoorin_progress. - Run
kotgent task show <ref>for every selected row. Use the full detail, including body, dependencies, linked sessions, and activity; do not reconcile from list titles alone. - Record HEAD, branch or detached state, and
git status --shortso the report identifies its snapshot.
Inspect repository evidence in this order
- Read applicable
AGENTS.mdandCLAUDE.mdfiles first. Treat them as constraints, not backlog items. - Find active plan and backlog files. Exclude completed, superseded, archived, or historical plans unless they explain a mismatch.
- Inspect the implementation and tests named by tasks or plans. Use exact symbols, paths, assertions, and observable behavior as evidence.
- Search tracked content for relevant
TODOandFIXMEmarkers. Do not promote every marker into a task; require a concrete match to intended repository work. - Inspect relevant Git history with focused
git log,git show, orgit blame. Use commit IDs when history proves completion, replacement, or architectural change. - Include relevant uncommitted and untracked work from
git status; never treat a clean HEAD as the whole repository when the worktree contains evidence.
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 · 79 lines · 69 tokens per session scan A 39a517ca6ec5
sync-tasks is a skill published in the GitHub repository Heapy/kortex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,094 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
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
improve-website
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging…
skills-manager-cli
Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…
ln-51-opportunity-evaluator
Evaluates new product directions using current demand, acquisition, competition, economics, and validation evidence. Use before commitment; not for backlog or implementation planning.
ppt-design-skill
Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.