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/voxtechnologies/transmute-framework/prelaunchnpx skills add VoxTechnologies/transmute-framework --skill prelaunchgit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWhat 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 | $0.00083 | $0.03302 |
| Opus 5 | $0.00042 | $0.01651 |
| Sonnet 5 | $0.00017 | $0.00660 |
| Haiku 4.5 | $0.00008 | $0.00330 |
Grade A, and why
prelaunch 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 3d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 6H: Final Check Before Production Deployment
Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/prelaunch-detailed-guide.md for the complete verification procedures, checklist templates, and report format.
Lead a multi-agent pre-launch verification project. Perform a comprehensive final check of the COMPLETE product before it goes live. This is the last gate between development and real users.
Stage Sequence (recommended ordering): Stage 5B → 6A/6B/6C (parallel) → 6E → 6F → 6G → 6D (Documentation) → 6H (this stage) → 6V (Verification) → [6R] → 6P or 6P-R → 7 (Deploy) → 7V → 7D
Prerequisites
Verify before starting — this stage has the strictest prerequisite checks:
./plancasting/_audits/implementation-completeness/report.mdexists with PASS or CONDITIONAL PASS. If missing, STOP — 5B is a prerequisite gate. CONDITIONAL PASS requires each Category C issue to have a documented workaround. FAIL means STOP.- ALL Stage 6 audit reports exist:
./plancasting/_audits/security/report.md(6A)./plancasting/_audits/accessibility/report.md(6B)./plancasting/_audits/performance/report.md(6C)./plancasting/_audits/documentation/report.mdand./docs/(6D) — mandatory for software products; skip only if plancasting/tech-stack.md indicates non-software product or documentation explicitly marked N/A./plancasting/_audits/refactoring/report.md(6E)./seed/README.mdand./plancasting/_audits/seed-data/report.md(6F) — skip if plancasting/tech-stack.md indicates N/A./plancasting/_audits/resilience/report.md(6G) For any missing report (except 6D/6F if skipped), STOP — prerequisite not completed. For each existing report, read its## Gate Decisionheading and verify the gate passed. If any shows FAIL, STOP. If CONDITIONAL PASS, verify the conditions are acceptable for launch.
- Check for unfixable violation files from prior stages (not all stages produce these):
./plancasting/_audits/security/unfixable-violations.md,./plancasting/_audits/accessibility/unfixable-violations.md,./plancasting/_audits/performance/unfixable-violations.md,./plancasting/_audits/refactoring/unfixable-violations.md,./plancasting/_audits/resilience/unfixable-violations.md,./plancasting/_audits/documentation/unfixable-violations.md,./plancasting/_audits/seed-data/unfixable-violations.md. If any exist, read them and treat CRITICAL items as launch blockers. If a file does not exist, that stage had no unfixable violations — skip it. - Read
./CLAUDE.mdand./plancasting/tech-stack.mdfor project conventions.
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.
- 3d ago First seen · 201 lines · 83 tokens per session scan A 5f9ee7f34ae7
prelaunch is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 3,302 once invoked, about $0.0004 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
taiyi-integration
TaiyiForge 第9阶段 — 闭环归档，CHANGELOG.md。四端通用。.
release
Prepare and publish Perigon.CLI patch releases, including versioning, release notes, bilingual docs, validation, and the nuget-branch CI handoff.
release-and-distribution
Release and Distribution Steward.
ship
Finalizes tests/docs/changelog and merges the PR to make it deployment-ready.
update-changelog
Updates a project changelog with entries for changes since the branch diverged from main. Use when about to open a PR, cutting a release, or when the user asks about changelog, release notes, or migration notes.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.