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 skills add Heapy/kortex --skill make-plangit clone --depth 1 https://github.com/Heapy/kortexWrote 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/heapy/kortex/make-plan)<a href="https://agentmods.dev/skills/heapy/kortex/make-plan"><img src="https://agentmods.dev/badge/skills/heapy/kortex/make-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/heapy/kortex/make-plan"><img src="https://agentmods.dev/badge/skills/heapy/kortex/make-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.01012 |
| Opus 5.5 | $0.00018 | $0.00405 |
| Sonnet 5.5 | $0.00009 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
make-plan 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 13d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Plan
Produce an approved, task-owned plan through the kotgent CLI. Approval ends this workflow; it does
not start implementation. Keep existing Markdown plans usable when the user asks to revise one, and
migrate one to a task only when that is part of the request.
Establish the task and caller
Read the repository's instructions, resolve its Git root, and check git status --short and
kotgent --version. Require a CLI with kotgent plan support. Use the current live pane as caller.
Outside a Kotgent pane, use --session ID only when the user or invocation context supplied that exact
Kotgent session ID. Never derive it from an environment variable, provider conversation, name, cwd,
recency, or kotgent list.
If the user named a task, read it with kotgent task show REF. Otherwise use kotgent task show to
resolve the linked task. Append the explicit --session ID to every caller-dependent command only in
outside-pane mode. If there is no linked task, inspect the repository's project backlog for the requested
work; create one focused task with the kotgent:create-tasks workflow when needed. Preserve its
provenance and project rules. Do not initialize/restore a project or guess a caller to get past a failure.
Keep one explicit task reference for all plan commands. Read kotgent plan show REF; a missing plan
is expected for a new task, but an authentication or connection error is not evidence of absence.
Build a reviewable plan
Read relevant code, tests and user constraints. Ask one focused question at a time only when its answer changes the plan; continue independent investigation while waiting. Do not fill missing requirements with unrelated cleanup or speculative features.
Use the document contract for JSON, IDs, limits and dependencies. Explain the outcome and constraints, the concrete implementation choices, focused tasks with file ownership and verification, and any consequential unresolved decisions. Include dependencies only when they constrain execution. Choose task boundaries that can be implemented and reviewed in separate worker worktrees.
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.
- 13d ago First seen · 77 lines · 44 tokens per session scan A 95d18b1ff2df
make-plan is a skill published in the GitHub repository Heapy/kortex (7 stars, last pushed 7d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,012 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
murmur-review-loop
Use when the user says 'send this to my client', 'get feedback on this page', 'send a review link', 'what did the client say', or 'work through the review notes'. Sends a Murmur review link, reads the notes reviewers pin to the page, replies, applies each change on a duplicate, and resolves every note with the…
glab-gitlab-issue
Read and manage GitLab issues through the glab CLI. Use when a user provides an issue ID and repository and asks to view issue details, comments, or uploaded images, publish comments, update assignees or labels, or manage issue time tracking (estimate/spent time) without using the web UI.
escalate
Escalate a support ticket to a Linear issue and notify the team on Slack.
auto-tag
Automatically analyze and tag untagged Gorgias tickets based on content.
bug-report
Extract a structured bug report from a support ticket and create a Linear issue.
freshdesk-triage
Pull open tickets from Freshdesk and triage by priority, type, and SLA.