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/clarifynpx skills add melodic-software/claude-code-plugins --skill clarifygit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWhat 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 | $0.00173 | $0.03280 |
| Opus 5 | $0.00086 | $0.01640 |
| Sonnet 5 | $0.00035 | $0.00656 |
| Haiku 4.5 | $0.00017 | $0.00328 |
Grade A, and why
clarify 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify a dense artifact into something you can act on
You were just handed a wall of text, an interview round with seven cross-referenced questions, a design memo thick with session jargon. This skill takes that exact artifact and makes it clear enough to act on: one decision at a time, jargon defined, and the actual choices pulled to the surface.
The move is clarify by restructuring, never by simplifying. The content stays at full precision and full reading level; only its arrangement changes. Lowering the altitude is a different job (see Boundaries). That means plain words, an analogy, ELI5. A clarification that loses or softens a decision is worse than the wall of text, so the fidelity rules below are hard, not aspirational.
The core move
- Identify the target. With an argument, that is the thing. Empty argument → the previous assistant response (see Empty argument).
- Ground it, don't recall it. Re-read the actual artifact this turn, the message just sent, in full. Working from your memory of it instead of its text is how operative terms drift.
- Restructure faithfully. Chunk, define jargon, surface decisions (below), under the fidelity rules.
- Choose the medium. Artifact, local file, or terminal, per Rendering.
Empty argument, anaphora default
With no argument, the target is the assistant's own previous response, the thing the reader is reacting to. "Make this clear" needs no topic named: re-read that prior message and clarify it. When there is no prior assistant message, a cold start where the reader opens with "make this clear" and nothing has been said, do not invent a target: ask what to clarify.
Trivial-target escape hatch. When the resolved target holds fewer than ~2 decisions, a short answer, a status line, anything with nothing to untangle, do not run the full table/glossary apparatus on it. Say in one line that the target has nothing dense to clarify, and ask what the reader actually wanted clarified. A three-line response restructured into a one-row decision table is ceremony, not clarity.
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 · 241 lines · 173 tokens per session scan A 1cb519209685
clarify is a skill published in the GitHub repository melodic-software/claude-code-plugins (12 stars, last pushed 2d ago), licensed MIT. It adds 173 tokens to every session and 3,280 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 2026-08-30.
Other skills, from other repositories
deep-research
Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore…
error-ux
Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.
adversarial-patterns
Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.
documentation-testing
Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.
adversarial-analysis
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.