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/compressnpx skills add melodic-software/claude-code-plugins --skill compressgit 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/compress)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/compress"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/compress.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 | $0.00233 | $0.04289 |
| Opus 5 | $0.00117 | $0.02145 |
| Sonnet 5 | $0.00047 | $0.00858 |
| Haiku 4.5 | $0.00023 | $0.00429 |
Grade C, and why
compress scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$(dirname "<absolute-path-from-step-1>")" How it starts
The opening of the file, as written. The whole thing — 158 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 .md files (empty = none matched or the probe returned nothing): !git status --porcelain >/dev/null 2>&1 && { git status --porcelain 2>/dev/null | grep -E '\.md"?$' | head -10; :; } || echo "(git status unavailable)"
Purpose
Markdown in docs/, README files, onboarding docs, third-party pasted prose, and drifted skill bodies accumulates FLAVOR. Filler ("just", "really", "basically"), hedging ("perhaps", "might"), articles, pleasantries. context/flavor-vs-content-matrix.md defines FLAVOR (safe to cut) vs CONTENT (never cut). The batch fan-out path (Phase A LATITUDE) is a word-level trimmer: mechanical drops + passive→active + nominalization only. No sentence-level restatement deletion. The single-file in-session Edit fallback may apply the full matrix taxonomy (including redundant restatement of bold rule names) behind the same semantic-diff net. Always-loaded instruction files (.claude/rules/**, AGENTS.md, CLAUDE.md, **/SKILL.md) bound empirically at 2-3% yield (see ## Sources). Likely 5-15% yield on author-time-undisciplined content when the Edit fallback's broader latitude applies; batch fan-out yields are correspondingly smaller.
Methodology: snapshot original → backend mechanical compression (the caveman plugin via /caveman:compress, OR in-session Edit fallback) → spawn semantic-diff subagent comparing original vs condensed (output: SEMANTIC LOSS / AMBIGUITY / FALSE POSITIVE per finding with verbatim citations) → revert every SEMANTIC LOSS + AMBIGUITY → run markdownlint-cli2 → ship or revert.
Backend selection
Default-action Step B picks the mechanical-compression backend: the caveman plugin (marketplace caveman, invoked as /caveman:compress via the Skill tool) when present, otherwise the in-session Edit-based fallback. Caveman performs the mechanical flavor cuts (articles, fillers, hedging, verbose-verb collapses) as the compression backend. It is NOT the verification gate. Fallback policy is graceful: the in-session Edit-based path substitutes whenever caveman is absent or unwanted. Subsequent steps (semantic-diff dispatch, revert pass, markdownlint) wrap the output regardless of backend choice.
What ships with it
15 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.
- context/fan-out-orchestration.md 5.8 KB
- context/flavor-vs-content-matrix.md 5.4 KB
- context/integration.md 5.2 KB
- context/semantic-diff-prompt.md 4.8 KB
- context/target-types.md 8.2 KB
- evals/evals.json 12 KB
- evals/fixtures/audit-fixture-dir/lean.md 528 B
- evals/fixtures/audit-fixture-dir/mixed.md 719 B
- evals/fixtures/audit-fixture-dir/verbose.md 1.8 KB
- evals/fixtures/terse-agent.md 349 B
- evals/fixtures/verbose-onboarding-snippet.md 602 B
- scripts/audit-scan.sh 4.9 KB runs code
- scripts/audit-scan.test.sh 3.4 KB runs code
- scripts/detect-caveman.sh 1.6 KB runs code
- scripts/detect-caveman.test.sh 3.5 KB runs code
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.
- yesterday First seen · 158 lines · 233 tokens per session scan C 04995323b335
compress is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 233 tokens to every session and 4,289 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
generate-tree-structure
For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.