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/audit-completenessnpx skills add VoxTechnologies/transmute-framework --skill audit-completenessgit clone --depth 1 https://github.com/VoxTechnologies/transmute-frameworkWrote 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/voxtechnologies/transmute-framework/audit-completeness)<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/audit-completeness"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/audit-completeness.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.04648 |
| Opus 5 | $0.00046 | $0.02324 |
| Sonnet 5 | $0.00018 | $0.00930 |
| Haiku 4.5 | $0.00009 | $0.00465 |
Grade A, and why
audit-completeness 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transmute Audit Completeness — Stage 5B: Implementation Completeness Audit
Lead a multi-agent implementation completeness audit using Claude Code Agent Teams. Systematically verify that EVERY feature in the PRD has been FULLY implemented — not just scaffolded — and fix any gaps found.
Read the detailed guide at ${CLAUDE_SKILL_ROOT}/references/audit-completeness-detailed-guide.md for the complete teammate instructions, scan scripts, fix patterns, and coordination protocol.
Why This Stage Exists
Stage 5 (Feature Implementation) builds all features sequentially. In practice, a recurring pattern emerges: backend implementations are thorough and complete, but many frontend components remain as stubs — scaffold-quality code with placeholder text, unconnected hooks, missing interactive behavior, or components that exist in files but are never rendered. This happens because:
- Even with the pipeline model's full context window (see tech-stack.md § Model Specifications), quality degrades over extended sessions (beyond the session feature limit) as accumulated context competes with per-feature attention
- Per-feature quality gates become less rigorous as the session progresses
- Frontend teammates produce "looks done" output that passes a fatigued quality gate
This stage runs with a FRESH context window, focused SOLELY on finding and fixing these gaps. It is the hard gate between implementation and QA.
Category System (Size-Based — Different from 6V/6R)
Issues found during this audit are classified into three SIZE-BASED categories:
- Category A: <30 non-blank non-comment lines per affected file — stub text replacement, dead links, missing simple states
- Category B: 30–100 lines per file AND <150 lines total across affected files — component body rebuild, form handler wiring, modal content population
- Category C: ≥100 lines in any single file OR ≥150 lines total across all affected files OR unbuilt features — escalate to Stage 5 re-run
This differs from Stage 6V/6R, which classifies by FIXABILITY (A = auto-fixable, B = semi-auto, C = needs human judgment). Size-based categories here determine whether the fix is small enough for a 5B teammate to handle or requires a full Stage 5 re-run.
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 · 252 lines · 91 tokens per session scan A 5839306d23b6
audit-completeness is a skill published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 4,648 once invoked, about $0.0005 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-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…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
evaluating-code-models
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.