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/maintainnpx skills add VoxTechnologies/transmute-framework --skill maintaingit 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 | $0.00086 | $0.03810 |
| Opus 5 | $0.00043 | $0.01905 |
| Sonnet 5 | $0.00017 | $0.00762 |
| Haiku 4.5 | $0.00009 | $0.00381 |
Grade A, and why
maintain 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 2d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Maintenance — Stage 9
Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/maintain-detailed-guide.md for the complete maintenance procedures, teammate spawn prompts, update strategies, and report templates.
Context
Designed to be run on a regular cadence (monthly or quarterly) to keep the codebase healthy. Outdated dependencies accumulate security vulnerabilities, miss performance improvements, and eventually create painful migration cliffs.
Prerequisites
- Read
CLAUDE.mdandplancasting/tech-stack.md. - Ensure
git statusshows a clean working directory. Commit or stash all uncommitted changes. - Check
plancasting/tech-stack.mdfor theSession Languagesetting. Generate all reports in the specified language. - Infer package manager from lock files if CLAUDE.md Part 2 'Commands' section is empty:
bun.lockb-> bun,package-lock.json-> npm,pnpm-lock.yaml-> pnpm. Log the inferred package manager in the report.
Inputs
- Codebase: Complete project directory
- Tech Stack:
./plancasting/tech-stack.md - Project Rules:
./CLAUDE.md - Lock file:
package-lock.json,bun.lockb, orpnpm-lock.yaml
Stack Adaptation
Examples use bun commands. Adapt to your package manager:
npm audit-> Bun has no built-in audit. Usenpm auditifpackage-lock.jsonexists; otherwise usebunx audit-ciornpx snyk test. Document which audit tool was used in the report.npm update->bun updatenpm outdated->bunx npm-check-updates(Bun has no built-inoutdatedcommand) Always readCLAUDE.mdandplancasting/tech-stack.mdfor actual conventions.
Execution Flow
Phase 1: Lead Analysis and Planning
Branch safety: Create a dedicated branch: git checkout -b chore/dependency-update-$(date +%Y-%m-%d-%H%M%S). The HMS suffix prevents collisions if Stage 9 is re-run the same day. Do NOT commit directly to main.
Pre-flight Concurrency Check: Before proceeding, verify that Stage 8 (Feedback Loop) is not currently in progress. Check: (1) git log --oneline -5 | grep -i 'feedback' — if the most recent commit is an in-progress feedback batch from the current day, STOP; (2) git branch --list 'feedback/*' — if a feedback/batch-* branch exists, Stage 8 may be active. Do not run Stage 9 concurrently with Stage 8 (both modify package.json and lock files). Wait for Stage 8 to complete and commit before starting Stage 9.
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.
- 2d ago First seen · 221 lines · 86 tokens per session scan A 363633d69b3d
maintain is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 3,810 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
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…
peer-review
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
statistical-power
Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…