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/threadWrote 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/thread)<a href="https://agentmods.dev/skills/mishahanin/heading-os/thread"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/thread/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/thread"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/thread.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 | $0.00074 | $0.02003 |
| Opus 5.5 | $0.00030 | $0.00801 |
| Sonnet 5.5 | $0.00015 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
thread 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 1mo 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/thread - Operational Threads Registry
Manages running state of business and personal life situations across sessions. Distinct from CRM (people), pipeline (deals), ZK (ideas), outputs (artifacts).
Spec: build/spec/docs/superpowers/specs/2026-04-29-threads-registry-design.md (data overlay: under .heading-os-data/build/spec/)
When to use
| Trigger | Action |
|---|---|
| Multi-step external situation that has follow-through across sessions | open |
| Recurring project (HEADING book, ODUN.ONE x TrustONE, SPL) | open |
| Personal life thread (medical, family, travel) | open with type personal |
| Outbound communication on an existing thread | log with --artifact |
| Decision made on an active thread | log --decision "..." |
| Pending action surfaced | log --follow-up "..." |
| Follow-up completed | log --done <index> |
| Thread done | close --reason "<why>" |
| Thread paused for weeks | hold --reason "<why>" |
| Thread reactivates | reopen |
| Operator says "do not remind me about this until " | quiet --until <date> |
| Operator says "freeze this, I will raise it myself" | quiet --indefinite |
| Quiet period is over | quiet --clear |
| Survey active threads | list |
| Lookup by keyword | find <query> |
| Read full thread | show <id> |
| /prime archive scan | archive-scan --apply |
When NOT to use
- Code work, debugging, technical fixes - explicitly out of scope.
- Single emails to new contacts - use
/email-draft. - Knowledge notes / insights - use
/zk. - CRM contact logs - use
/crm. - Anything inside
_secure/- the vault has its own audit log via_secure/.audit-log.md.
Approval gate (always)
I never open or log silently. Before invoking the CLI, I ask:
"This looks like a thread, or part of the [Quillon] thread. Open it, or log to it?"
The user approves, modifies, or skips. After several months of trusted use, this gate may be relaxed - deferred to v2.
CLI
python3 scripts/thread.py open <business|personal> "<title>"
python3 scripts/thread.py log <thread-id> "<event>" [--artifact PATH ...] [--decision TEXT ...] [--follow-up TEXT ...] [--done INDEX]
python3 scripts/thread.py close <thread-id> --reason "<why it is retired>"
python3 scripts/thread.py hold <thread-id> --reason "<why it is retired>"
python3 scripts/thread.py reopen <thread-id>
python3 scripts/thread.py list [--type business|personal] [--status active|on-hold|closed]
python3 scripts/thread.py find "<query>"
python3 scripts/thread.py show <thread-id>
python3 scripts/thread.py quiet <thread-id> [--until YYYY-MM-DD | --indefinite | --clear]
python3 scripts/thread.py archive-scan [--apply]
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.
- 1mo ago Changed · +11 lines 8426a75ac237
- 1mo ago Changed · +1 lines ebc91e1b49ae
- 1mo ago First seen · 175 lines · 74 tokens per session scan A 865b9354eb77
thread is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,003 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
file-collect-sort-action
Erkennt Nutzeraufträge der Form "hole aus einem Ordner immer bestimmte Dateien und sammle sie an einem Ziel" und richtet dafür das Modul file-collect-sort-action (CLI fcsa) ein — ein konfigurationsgetriebener Agent, der Ordner scannt, Dateien per Schablone kategorisiert und gestufte Aktionen anwendet…
simplify-code
Parallel 4-agent cleanup of recent code changes.
request-progress
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story, so My Work shows progress meters, shipping velocity and learned working preferences. Use when asked to "group requests", "group by overall request", "review…
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
first-task
Run the first task chat that setup hands off.
initiate-setup
Run the first-run setup chat in the Hermes desktop app.