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/dissolve-commentsnpx skills add melodic-software/claude-code-plugins --skill dissolve-commentsgit 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 | $0.00252 | $0.02889 |
| Opus 5 | $0.00126 | $0.01444 |
| Sonnet 5 | $0.00050 | $0.00578 |
| Haiku 4.5 | $0.00025 | $0.00289 |
Grade A, and why
dissolve-comments 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 — 161 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"
Uncommitted code files (preview, first 10; empty = none matched or the probe returned nothing): !git status --porcelain -z >/dev/null 2>&1 && { git status --porcelain -z 2>/dev/null | awk 'BEGIN { RS = "\0" } skip { skip = 0; next } { if (substr($0, 1, 2) ~ /[RC]/) skip = 1; print substr($0, 4) }' | grep -Ei '\.(cs|ts|tsx|js|jsx|py|sh|ps1|go|rs|java|rb|lua|sql|c|h|cpp|hpp|yaml|yml|toml)$' | head -10; :; } || echo "(git status unavailable)"
Variables
Arguments: $ARGUMENTS
Purpose
The enforcement counterpart to /code-tidying:audit-comment-residue: where that skill classifies
and reports, this one edits. It makes the code in scope self-describing and expressive, and it removes
every comment there that does not earn its keep, with "earn its keep" defined by the doctrinal floor the
canonical sources jointly sign: implementation code only needs comments when the code is
nonobvious (Martin ⇄ Ousterhout debate), restated by Anthropic's own guidance as "Only add
comments where the logic isn't self-evident."
The prime driver is agent-written code, which over-narrates by default. This is deliberately a tidy-after-generation pass, not a generation-time comment ban. Comments are useful model context while code is being written; they are dissolved after.
The three-way triage
Every comment in scope gets exactly one classification. Full doctrine, the earn-its-keep test, and worked examples: reference/triage.md.
| Class | Test | Treatment |
|---|---|---|
| A, zero/negative information | Restates adjacent code, obsolete, commented-out code | Delete outright, deletion is the complete treatment |
| B. Information code could carry | The comment compensates for a naming/structure deficiency | Refactor until the comment is superfluous, then delete, never delete first |
| C. Information code cannot carry | Why/rationale, constraint, warning, contract (units, invariants, side effects) | Keep only if load-bearing at the point of reading; terse by default. Improve wording if needed |
What ships with it
4 files 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 · 161 lines · 252 tokens per session scan A e717c1e80832
dissolve-comments is a skill published in the GitHub repository melodic-software/claude-code-plugins (12 stars, last pushed 2d ago), licensed MIT. It adds 252 tokens to every session and 2,889 once invoked, about $0.0013 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.