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 naimkatiman/continuous-improvement --skill launchgit clone --depth 1 https://github.com/naimkatiman/continuous-improvementWrote 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/naimkatiman/continuous-improvement/launch)<a href="https://agentmods.dev/skills/naimkatiman/continuous-improvement/launch"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/launch/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/naimkatiman/continuous-improvement/launch"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/launch.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 | $0.00113 | $0.04098 |
| Opus 5.5 | $0.00045 | $0.01639 |
| Sonnet 5.5 | $0.00023 | $0.00820 |
| Haiku 4.5 | $0.00011 | $0.00410 |
Grade A, and why
launch 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- launch — 88% identical, 89 lines differ
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch
Launch is the shipyard's delivery run: from mission brief to shipped, verified change. It stands on the verifiability boundary — agents continuously run everything repeatable and acceptable-by-evidence; humans decide what cannot be judged by the system or what fails expensively. The goal is not maximum automation — it is maximum delegation of verifiable work, so the human's time is spent only on the decisions only a human can make.
The verifiability test, applied to every step: if this is done wrong, can the system detect it? Can it redo or roll back automatically? Both yes → agent. No unique answer, system cannot judge, or expensive to get wrong → human.
Launch assumes the shipyard exists — and refuses to run if it does not. The yard gate is the first action of every invocation, before document-language resolution and before reading any supplied spec:
- Run the full drydock
--checkaudit — missing surfaces, a missing or invalidCONTEXT.mdfrontmatterdocumentLanguage, dead paths, glossary terms unused in code, standards never referenced. This is the single criterion: Launch performs no separate facility inventory of its own. - Actionable / high-confidence findings hard-block the run: list every such finding verbatim, point at
/oh-my-claudecode:drydock, state that the run never started and no artifacts were produced, and stop. Without an explicit override, treat any finding as blocking. - Narrow override (explicit intent only): low-confidence findings, findings explicitly classified as false positives in the drydock report, or a scratch/throwaway repository explicitly declared by the user may be overridden only with deliberate, per-invocation user intent — the override must name the finding(s) or the throwaway scope and must never silently swallow a high-confidence actionable finding. No general bypass flag.
- Current audit limitation: today
--checkis a skill-instruction checklist without a machine-readable finding/severity contract or executable — severity classification relies on the drydock report's wording until a structured contract exists. A machine-readable finding/severity exit contract is the intended follow-up; the gate wording stays honest about what it can and cannot rely on mechanically. - A clean audit (or an explicitly overridden low-confidence/false-positive/scratch scope) admits the run. Every paper-trail slot (
CONTEXT.md,docs/adr/,docs/business/) and facility surface already exists at that point; Launch fills the paper trail as decisions settle but never creates the slots. - The rules entry is
CLAUDE.md— the shipyard map recognizes no substitute.
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 First seen · 153 lines · 113 tokens per session scan A 18f25b700e51
launch is a skill published in the GitHub repository naimkatiman/continuous-improvement (9 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 4,098 once invoked, about $0.0005 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 2026-09-08.
Other skills, from other repositories
ap-tasks
Use the agentproto shared task board — taskcreate, taskclaim (CAS with rev), tasklist, and taskupdate to coordinate parallel agents on one board, gate done with verify commands, and hand off work claimably. Trigger when coordinating parallel agents, splitting work across sessions, handing off tasks, or needing…
pb-nested-orchestrator
Spawn a parent agent that spawns and supervises its own sub-agents, forming a two-level tree on the agentproto daemon. Trigger for delegation depth - 'agent that spawns sub-agents', 'two-level agent tree', 'let an agent orchestrate on its own'.
supervise-long-missions
Route missions that outlive your attention — durable waiting, completion gates with retries, scheduled cron check-ins, shared task boards, spend tracking, and cleanup. Use when an agent works longer than one turn or you must not block on it. Triggers: supervise, long-running mission, check-in, non-blocking wait…
coordinator
Take over as coordinator of the current LangWatch drive: read the live state from disk (the lane roster, the newest handover, the shape counters), report it, then work the handover's next action by writing manifests and spawning lanes. Replaces pasting a brief out of a handover document - the state is read, never…
tencent-meeting-mcp
A Tencent Meeting assistant for scheduling meetings and working with participants, recordings, transcripts, and AI-generated meeting notes.
rem-project-sessions
Write or update one project page from the owner's messages and a bounded packet of local project evidence.