Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/nextWrote 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/mishahanin/heading-os/next)<a href="https://agentmods.dev/skills/mishahanin/heading-os/next"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/next/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/mishahanin/heading-os/next"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00166 | $0.01311 |
| Opus 5 | $0.00083 | $0.00656 |
| Sonnet 5 | $0.00033 | $0.00262 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
next 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 8d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next (state-aware recommender)
Tell the CEO the logical next move and the exact command — grounded in what just happened, not a generic menu. Read-only: name the command, never run it.
Phase 0: Gather the signal
- Run the "what just happened" reader:
It returns a ranked recent-actions list, newest first and handoff-weighted. The four sources are the session handoff pointer (python scripts/next-signal.py --jsonoutputs/operations/handoff-archive/.latest/summary.md), the newestoutputs/files with noise dirs excluded, recentgit logsubjects, and activethreads/business/files. If it exits non-zero ("outputs unreadable" and the like), say so plainly and fall back to the handoff pointer alone. - Load the relationship catalog accessor (do not read the whole CSV into context):
python scripts/skill_graph.py followers <skill> # next steps after a skill python scripts/skill_graph.py by-output-dir <path> # which skill produced a recent output
Phase 1: Match
- For each recent action, map it to its producing skill. Use
skill_graph.py by-output-diron the output's directory, or map directly when the handoff or commit names the work. - Look up that skill's
followed_byedges. The handoff pointer is the strongest signal (explicit human intent); outputs/git/threads are supporting inference.
Phase 2: Recommend
- Emit 2–4 ranked recommendations, each one line:
{what just happened} → run /{skill} ({one-line why}). - Order optional steps first and any genuinely-gated next step after them. Say which is which.
- Honesty floor: if no edge is strong enough, emit nothing rather than a weak guess. "Nothing obvious is queued — the last clear action (
{X}) has no strong next step. Tell me the area and I'll point you." beats a fabricated recommendation. - Read-only. Name the slash-command; never invoke it. The CEO decides and runs it (CEO sovereignty;
.claude/rules/prompt-refinement.mdPhase 3). Recommend running the chosen step in a fresh context where it is heavy.
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.
- 8d ago First seen · 105 lines · 166 tokens per session scan A 196bcfe8af5a
next is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 166 tokens to every session and 1,311 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
devops-expert
Expert-level DevOps practices, culture, automation, and continuous delivery. Use when the user mentions CI/CD, automation, infrastructure, or culture, or when the task involves DevOps Culture or Culture & Process.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.