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 melodic-software/claude-code-plugins --skill wait-whatgit 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/wait-what)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/wait-what"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/wait-what/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/melodic-software/claude-code-plugins/wait-what"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/wait-what.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 | $0.00062 | $0.00680 |
| Opus 5.5 | $0.00025 | $0.00272 |
| Sonnet 5.5 | $0.00012 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
wait-what 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 8d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wait. What?
I lost track of your last reply. Go back to the last point I clearly followed and explain again from there, adding the context I was missing. Write it in ASD-STE100 Simplified Technical English (short sentences, one meaning per word, technical terms exact) and use the terms the project itself uses for its domain. Read the nearest domain glossary or context map, per the project's own convention, when one exists; with none, plain technical English alone.
A declared species in this plugin: NOT a corrector
Every sibling corrector re-anchors a standing discipline through the
re-anchor/audit/correct loop. This skill is a one-shot, user-fired
communication repair: the human, the only party who can detect that a message
did not land, fires it, and the re-pitch IS the repair. Nearest siblings, for
routing:
/discipline:tighten-your-output when the problem is too many words, and
/discipline:mind-your-maxims when the standing cooperative-communication
discipline itself needs re-anchoring; this skill repairs the one message that
lost its reader.
Boundaries
- Never model-invoked.
disable-model-invocation: trueis load-bearing: the model cannot detect that its reader stopped following, so an auto-fired re-pitch would be incoherent. - Re-pitch means re-ground, not compress. Full technical precision stays; the premise the reader was missing comes back. A re-pitch that is shorter and blunter, but no clearer, is the failure this skill exists to avoid.
- Pick the sibling that fits the gap (both in other plugins, if installed).
/education:explaindrops any concept, code or error, or the last message, to plain words with an analogy and climbs back up only on request; use it when the reader needs the idea simplified, not the message re-grounded./adhd:clarifyreorganizes a dense, decision-heavy message into one decision at a time with its precision and terms unchanged; use it when the message has the right content in the wrong shape. This skill re-pitches the one message that lost the reader: missing context back, in Simplified Technical English, at full precision. - No glossary is a no-op, not an error. The vocabulary half degrades silently; the register and missing-context halves always apply.
- Excluded from batch sweeps. No
discipline-batchtier on purpose: a sweep must never fire a repair only the human can call for.
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.
- 8d ago Changed · +1 lines · -12 tokens per session 58ed81c3338d
- 17d ago Changed · +8 lines 0b0ff0985f0c
- 1mo ago Changed · +2 tokens per session 02a89bec97f3
- 1mo ago Changed · -1 lines 5f3e5666096f
- 1mo ago First seen · 44 lines · 72 tokens per session scan A 5eb1e1be5810
wait-what is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 680 once invoked, about $0.0002 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 2026-09-03.
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.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.
validate-before-process
For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.