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/melodic-software/claude-code-plugins/audit-answersnpx skills add melodic-software/claude-code-plugins --skill audit-answersgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/audit-answers)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/audit-answers"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/audit-answers.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 5.1 | $0.00181 | $0.02704 |
| Opus 5 | $0.00090 | $0.01352 |
| Sonnet 5 | $0.00036 | $0.00541 |
| Haiku 4.5 | $0.00018 | $0.00270 |
Grade A, and why
audit-answers 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Variables
Arguments: $ARGUMENTS
Purpose
Independent adversarial validation of a completed /planning:interview's answers. It runs over any filled decision ledger, whether the human hand-answered the rounds or the recommendations were auto-accepted, and hands each answer to fresh-context agents that re-examine it on its merits. Only the answers they challenge or reclassify come back to the human; the rest collapse to a one-line confirmation.
The value is a producer≠critic pass over decisions the producing session is structurally the worst judge of. It is sharpest when the answers were auto-accepted: /planning:interview's accept-shorthand takes the orchestrator's own recommendations at face value, the producer grading its own work. A hand-answered ledger benefits too: fresh validators that never saw the reasoning catch a decision made under the same session's blind spots.
This is validation, never derivation. It does NOT spawn subagents to invent answers. The interview contract already resolves every fact from the environment, so anything that reaches a round is a genuine decision, the never-auto class. A subagent asked to derive it only reinjects the orchestrator's framing and converges to accept-all at quadratic frontier cost with a false patina of verification. Fresh-context independence is real only for checking an answer, not for producing one. So the answers are accepted first, then checked.
Preconditions
A completed /planning:interview for the topic. The skill validates whatever answers that interview persisted, in whichever form it wrote them. It does not require any single artifact:
- an engineering session's
## BriefinPLAN.md(its resolved decisions, Captured assumptions, and Deferred questions with their arbiter tags); - the decision-tree ledger (
interview-checklist.mdin the memory slice), present only for sessions the interview emitted one for (≥2 open questions ormemode); - a general (non-engineering) session's shared-understanding summary in the memory slice.
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 · 102 lines · 181 tokens per session scan A 29238c849e80
audit-answers is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 181 tokens to every session and 2,704 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
use-class-for-state
For complex state: encapsulate multiple interacting variables, stateful algorithms, backtracking search state.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.